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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enumerator
    -0.07
    yre
    -0.06
     functioning
    -0.06
    urbed
    -0.06
     polyline
    -0.06
     Kaiser
    -0.06
    enumer
    -0.06
    ameron
    -0.06
    arda
    -0.06
    .IsNotNull
    -0.06
    POSITIVE LOGITS
     зна
    0.07
     devez
    0.06
    Motor
    0.06
     motiv
    0.06
     Orch
    0.06
     Motor
    0.06
     macros
    0.06
     injust
    0.06
     Mens
    0.06
    _peng
    0.06
    Act Density 0.087%

    No Known Activations