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

    Neuronpedia

    INDEX
    Explanations

    phrases that express assistance or actions being performed for the reader

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

    you, me, him, us

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.53
     BoxFit
    -0.48
    ArrowToggle
    -0.46
    AnimationsModule
    -0.46
     Exactos
    -0.42
     tartalomajánló
    -0.41
    -0.41
    rungsseite
    -0.37
    Portail
    -0.36
    principalColumn
    -0.35
    POSITIVE LOGITS
     мәкал
    0.54
     հղումներ
    0.49
    automated
    0.45
     собі
    0.43
    madol
    0.42
    Manually
    0.42
     automati
    0.42
    belief
    0.41
     Automatically
    0.41
     automation
    0.40
    Act Density 0.032%

    No Known Activations