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

    Neuronpedia

    INDEX
    Explanations

    new discoveries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Power
    -0.07
    —
    -0.07
    .Retrofit
    -0.07
    drawable
    -0.06
    hecy
    -0.06
    .cert
    -0.06
    _pieces
    -0.06
    ウス
    -0.06
    _out
    -0.06
    _EVENT
    -0.06
    POSITIVE LOGITS
     mListener
    0.07
     dej
    0.07
     професси
    0.07
     lider
    0.07
     stringWith
    0.07
    uple
    0.06
     yazılım
    0.06
    iode
    0.06
     기반
    0.06
     gj
    0.06
    Act Density 0.060%

    No Known Activations