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

    Neuronpedia

    INDEX
    Explanations

    K

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rectangles
    -0.06
    Degree
    -0.06
     Geh
    -0.06
    .network
    -0.06
    arrera
    -0.06
     whitelist
    -0.06
    _small
    -0.06
     classify
    -0.06
     pu
    -0.05
     fram
    -0.05
    POSITIVE LOGITS
    ESH
    0.07
     asserting
    0.06
    /command
    0.06
    -space
    0.06
    แข
    0.06
    Advance
    0.06
    ามารถ
    0.06
    jsc
    0.06
     کودکان
    0.06
     جامع
    0.06
    Act Density 0.003%

    No Known Activations