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

    Neuronpedia

    INDEX
    Explanations

    static

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ats
    -0.07
    to
    -0.07
    ka
    -0.07
     Escape
    -0.06
    649
    -0.06
     opravdu
    -0.06
    409
    -0.06
     pracov
    -0.06
    ovaného
    -0.06
    yet
    -0.06
    POSITIVE LOGITS
    ）。↵
    0.07
     overwhelmed
    0.06
     bounding
    0.06
     Huffington
    0.06
    election
    0.06
    /classes
    0.06
     projekt
    0.06
    _choice
    0.06
    pars
    0.06
    (opt
    0.06
    Act Density 0.007%

    No Known Activations