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

    Neuronpedia

    INDEX
    Explanations

    say "m" word

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LOOKUP
    -0.08
    ArgumentException
    -0.07
     KP
    -0.07
    .FILL
    -0.07
     Wend
    -0.07
    _DEPTH
    -0.07
    .Set
    -0.07
     babes
    -0.06
    .setInput
    -0.06
    fake
    -0.06
    POSITIVE LOGITS
    详细了解
    0.07
    딛
    0.07
    .Sync
    0.07
    俪
    0.07
     ":"
    0.06
    결
    0.06
    륭
    0.06
     encounters
    0.06
    endale
    0.06
    :')↵
    0.06
    Act Density 0.000%

    No Known Activations