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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kidn
    -0.08
    ��
    -0.07
    SUM
    -0.07
     masturb
    -0.07
    forgot
    -0.07
     Marr
    -0.07
     दक
    -0.07
     losses
    -0.06
    stile
    -0.06
    -sw
    -0.06
    POSITIVE LOGITS
    -game
    0.07
     exemption
    0.06
    _genes
    0.06
    xff
    0.06
    ."]
    0.06
    Throwable
    0.06
    _components
    0.06
    ا�
    0.06
     CLIIIK
    0.06
    >(()
    0.06
    Act Density 0.000%

    No Known Activations