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

    Neuronpedia

    INDEX
    Explanations

    unix

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     logistic
    -0.07
    +(
    -0.07
     fundra
    -0.06
     thriving
    -0.06
    بری
    -0.06
     女
    -0.06
     ACCOUNT
    -0.06
    .Max
    -0.06
     occupied
    -0.06
    _result
    -0.06
    POSITIVE LOGITS
    DRAM
    0.08
    xFFF
    0.07
     یون
    0.07
    _ROUTE
    0.07
    _DGRAM
    0.07
    祖
    0.06
    IRR
    0.06
    ९
    0.06
     XK
    0.06
     outliers
    0.06
    Act Density 0.001%

    No Known Activations