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

    Neuronpedia

    INDEX
    Explanations

    bin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     )]↵
    -0.07
    AVA
    -0.07
    Binary
    -0.07
    ף
    -0.07
    评选
    -0.07
     momentum
    -0.07
     errs
    -0.07
     ]↵
    -0.07
    รอง
    -0.06
    LogLevel
    -0.06
    POSITIVE LOGITS
    Navig
    0.07
    ibal
    0.07
    hec
    0.06
    姚
    0.06
    estinal
    0.06
    就想
    0.06
    あ
    0.06
     Alloc
    0.06
    .il
    0.06
     새로
    0.06
    Act Density 0.003%

    No Known Activations