Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of hope and struggle related to human emotions and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding words before tokens "inside," "that," "were", .

    np_acts-logits-general · gemini-2.0-flash

    foreign words and abstract nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    interopRequire
    -0.62
     <<<<<<<<<<<<<<
    -0.59
    InjectAttribute
    -0.58
     metav
    -0.56
    findpost
    -0.56
    wissenschaften
    -0.56
    setVerticalGroup
    -0.54
    :✨
    -0.53
    WriteBarrier
    -0.52
     “¿
    -0.52
    POSITIVE LOGITS
    ova
    0.59
    faßt
    0.57
    chach
    0.56
     gdy
    0.56
    нье
    0.55
     champs
    0.55
    hede
    0.55
     
    0.54
     Masson
    0.53
     lecz
    0.53
    Act Density 0.166%

    No Known Activations