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

    Neuronpedia

    INDEX
    Explanations

    concentrations in scientific text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     normalization
    -0.07
    DetailsService
    -0.07
     Strings
    -0.06
     coins
    -0.06
     integr
    -0.06
     مذه
    -0.06
    ังก
    -0.06
     ､
    -0.06
    ีเอ
    -0.06
    getError
    -0.06
    POSITIVE LOGITS
    .fail
    0.07
    oseconds
    0.06
     immature
    0.06
    ↵↵↵↵↵↵
    0.06
     Gabriel
    0.06
    _expr
    0.06
    .clf
    0.06
    _jump
    0.06
    ротив
    0.06
     Rockets
    0.06
    Act Density 0.183%

    No Known Activations