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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BUTTON
    -0.07
    prus
    -0.07
     contributor
    -0.07
    ulant
    -0.07
    аном
    -0.07
     разных
    -0.06
    ibir
    -0.06
    wheel
    -0.06
     raid
    -0.06
    -sidebar
    -0.06
    POSITIVE LOGITS
    ))?
    0.07
     manageable
    0.06
     plaint
    0.06
    ('*',
    0.06
    �
    0.06
     zwar
    0.06
     Psycho
    0.06
    *l
    0.06
     solicit
    0.06
    ))*
    0.06
    Act Density 0.064%

    No Known Activations