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

    Neuronpedia

    INDEX
    Explanations

    expressions of contrast or transition in narrative

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

    change after initial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يكب
    -0.48
     almohada
    -0.45
     Vikipedi
    -0.45
     nahilalakip
    -0.44
     contemporaine
    -0.44
    iettivo
    -0.43
     magnética
    -0.40
    exitRule
    -0.39
     barat
    -0.39
     cortinas
    -0.38
    POSITIVE LOGITS
    sizeCache
    0.53
    //
    0.44
    IntoConstraints
    0.43
     وصلة
    0.42
     Initially
    0.41
    Initially
    0.41
     anfangs
    0.41
    原
    0.40
    舺
    0.40
     թվական
    0.40
    Act Density 0.224%

    No Known Activations