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
    jur
    -0.06
    Multiply
    -0.06
     McGu
    -0.06
     rab
    -0.06
     Definitions
    -0.06
    Sha
    -0.06
     q
    -0.06
     defenders
    -0.06
    _elements
    -0.06
    riterion
    -0.06
    POSITIVE LOGITS
    .Drawing
    0.07
    actually
    0.07
     comprehensive
    0.06
     gestion
    0.06
     동일
    0.06
     BASIC
    0.06
    金融
    0.06
    งท
    0.06
     formatter
    0.06
    712
    0.06
    Act Density 0.003%

    No Known Activations