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

    Neuronpedia

    INDEX
    Explanations

    key phrases related to definitions and comparisons

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

    essential, important, main

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.65
     betweenstory
    -0.64
     ProtoMessage
    -0.63
     تكبرها
    -0.57
    tagHelperRunner
    -0.57
    SharedCtor
    -0.52
    EDEFAULT
    -0.52
     defaultstate
    -0.51
     '\\;'
    -0.50
     PagesJaunes
    -0.50
    POSITIVE LOGITS
    RetentionPolicy
    0.38
     Rug
    0.38
    bital
    0.36
     toepassing
    0.36
    redos
    0.36
     feit
    0.35
    ✢
    0.35
     Sulfur
    0.34
     iron
    0.33
     root
    0.33
    Act Density 0.280%

    No Known Activations