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

    Neuronpedia

    INDEX
    Explanations

    aliyun code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kill
    -0.08
    _CLOSE
    -0.08
     Singh
    -0.07
    _new
    -0.07
     death
    -0.06
    笕
    -0.06
     fifo
    -0.06
    .Unicode
    -0.06
    \↵
    -0.06
    Soft
    -0.06
    POSITIVE LOGITS
     abundance
    0.07
    .Appearance
    0.07
    clusions
    0.07
     أع
    0.07
    лон
    0.07
    相當
    0.07
    指数
    0.07
    激光
    0.07
    -ap
    0.07
    .@
    0.07
    Act Density 0.001%

    No Known Activations