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
     الحرب
    -0.08
     watchers
    -0.07
    ดาว
    -0.07
    .deepEqual
    -0.07
     Both
    -0.07
     Influence
    -0.06
     OUTER
    -0.06
     Güvenlik
    -0.06
     rovněž
    -0.06
    Û
    -0.06
    POSITIVE LOGITS
     disease
    0.07
    (company
    0.07
    ียรต
    0.06
     councils
    0.06
    ристи
    0.06
     performance
    0.06
    oteca
    0.06
    аліз
    0.06
    }`,
    0.06
    050
    0.06
    Act Density 0.003%

    No Known Activations