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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ADER
    -0.07
    07
    -0.07
     Page
    -0.06
    08
    -0.06
    .BO
    -0.06
     �
    -0.06
    xBA
    -0.06
    02
    -0.06
     nạn
    -0.06
    osa
    -0.06
    POSITIVE LOGITS
    overnment
    0.07
     CONST
    0.07
    /{$
    0.06
    -прав
    0.06
    brook
    0.06
    enderror
    0.06
    兰
    0.06
    ymph
    0.06
    best
    0.06
    _timezone
    0.06
    Act Density 0.004%

    No Known Activations