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

    Neuronpedia

    INDEX
    Explanations

    or and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     java
    -0.06
    特殊
    -0.06
    ьте
    -0.06
     [].
    -0.06
     Flu
    -0.06
    oodles
    -0.06
    threat
    -0.06
    SP
    -0.06
    ace
    -0.06
     WS
    -0.06
    POSITIVE LOGITS
     annot
    0.07
     MAIL
    0.07
    @Repository
    0.07
     hodnocení
    0.07
    .DataBindings
    0.06
     gratuite
    0.06
     domination
    0.06
     अख
    0.06
    _PROP
    0.06
    _nat
    0.06
    Act Density 0.034%

    No Known Activations