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

    Neuronpedia

    INDEX
    Explanations

    phrases that include emphasis or strong descriptions

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

    words ending in ly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.46
     dodatk
    -0.43
     no
    -0.40
     However
    -0.40
     however
    -0.39
     solito
    -0.39
     wichtiger
    -0.39
    However
    -0.38
     tetapi
    -0.38
     natür
    -0.37
    POSITIVE LOGITS
    StructEnd
    0.80
    oredCriteria
    0.65
    :✨
    0.57
    Portail
    0.52
    InitVars
    0.52
    Personendaten
    0.52
     '\\;'
    0.51
    0.51
    AsUp
    0.50
    StoryboardSegue
    0.50
    Act Density 0.003%

    No Known Activations