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

    Neuronpedia

    INDEX
    Explanations

    range

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     harder
    -0.07
     yönetic
    -0.07
    Callbacks
    -0.07
     Towers
    -0.07
     těl
    -0.06
    $("
    -0.06
    .Dependency
    -0.06
    bet
    -0.06
     体
    -0.06
    船
    -0.06
    POSITIVE LOGITS
     ymin
    0.07
     uint
    0.07
    mute
    0.06
    \Data
    0.06
     discrepan
    0.06
     cardinal
    0.06
     bitrate
    0.06
     BF
    0.06
     acquainted
    0.06
     Range
    0.06
    Act Density 0.007%

    No Known Activations