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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vrier
    -0.09
     Innov
    -0.08
    areth
    -0.08
    .:↵↵
    -0.08
    .б
    -0.08
    :");↵↵
    -0.08
     bicic
    -0.08
     fogu
    -0.08
     μουσ
    -0.08
     {↵↵↵
    -0.08
    POSITIVE LOGITS
    0.07
    _nil
    0.07
     biased
    0.07
    nya
    0.07
     చె
    0.07
     nil
    0.07
     NIL
    0.07
     Lj
    0.07
    steuer
    0.07
     orchard
    0.07
    Act Density 0.000%
    No Known Activations