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

    Neuronpedia

    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fecha
    -0.06
    ovit
    -0.06
     смеш
    -0.06
    �ng
    -0.06
     악
    -0.06
    _attempts
    -0.06
    [MAXN
    -0.06
     Tao
    -0.06
    estone
    -0.06
     akce
    -0.06
    POSITIVE LOGITS
     Maine
    0.06
    illion
    0.06
    ства
    0.06
    esinin
    0.06
     awhile
    0.06
    /docs
    0.06
     身
    0.06
    LE
    0.06
     endanger
    0.06
    (open
    0.06
    Act Density 0.000%

    No Known Activations