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

    Neuronpedia

    INDEX
    Explanations

    Code/data descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ps
    -0.07
    ble
    -0.07
     Dave
    -0.06
    normalized
    -0.06
    gewater
    -0.06
    58
    -0.06
    "D
    -0.06
    607
    -0.06
    bars
    -0.06
    .clf
    -0.06
    POSITIVE LOGITS
    、、
    0.06
     LENGTH
    0.06
     neces
    0.06
    以外
    0.06
    iễn
    0.06
    ProcAddress
    0.06
    ebx
    0.06
    -exp
    0.06
    arya
    0.06
     defaultCenter
    0.06
    Act Density 0.227%

    No Known Activations