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

    Neuronpedia

    INDEX
    Explanations

    words that indicate prior actions or states of being

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

    Following "already"

    np_acts-logits-general · gemini-2.0-flash

    already followed by past participle or present perfect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    still
    -0.90
     still
    -0.85
     also
    -0.82
     todavía
    -0.82
     aún
    -0.81
     ainda
    -0.78
     Still
    -0.76
     fortfarande
    -0.76
    also
    -0.76
    Still
    -0.73
    POSITIVE LOGITS
    RenderAtEndOf
    0.97
    AsUp
    0.80
     للمعارف
    0.74
    RefNanny
    0.72
     begun
    0.71
    IsMutable
    0.70
     مفص
    0.69
    '>{
    0.67
    دانشنامهٔ
    0.67
    TestingModule
    0.67
    Act Density 0.083%

    No Known Activations