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

    Neuronpedia

    INDEX
    Explanations

    statements or claims related to legal arguments and assertions

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

    reporting claims or arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    delwed
    -0.50
     Normdatei
    -0.48
     esternos
    -0.47
    AutoScaleMode
    -0.46
     ویکی‌پدیا
    -0.46
    مراجع
    -0.41
    ++]=
    -0.40
    WebElementEntity
    -0.40
     ProtoMessage
    -0.40
    ++];
    -0.39
    POSITIVE LOGITS
    RefNanny
    0.44
    DrawerToggle
    0.40
    oneofs
    0.38
    sensitive
    0.36
    lcccc
    0.35
    expandindo
    0.35
     alleged
    0.35
     allegedly
    0.35
    accu
    0.34
    OCCURRED
    0.34
    Act Density 0.123%

    No Known Activations