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

    Neuronpedia

    INDEX
    Explanations

    disturb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    704
    -0.07
     Kelvin
    -0.07
    .bus
    -0.06
     axis
    -0.06
     �
    -0.06
    &a
    -0.06
    StreamWriter
    -0.06
    �
    -0.06
     slew
    -0.06
     společnost
    -0.06
    POSITIVE LOGITS
    _mD
    0.06
    lette
    0.06
    加入
    0.06
     exert
    0.06
     سر
    0.06
     PRE
    0.06
    Much
    0.06
     Skeleton
    0.06
    _tpl
    0.06
     reim
    0.06
    Act Density 0.004%

    No Known Activations