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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gaps
    -0.07
    ुण
    -0.07
    atial
    -0.07
    _Clear
    -0.06
     APA
    -0.06
    uploaded
    -0.06
    xFB
    -0.06
     Buckingham
    -0.06
    atinum
    -0.06
    MERCHANTABILITY
    -0.06
    POSITIVE LOGITS
     Seeking
    0.07
    Project
    0.06
    (cps
    0.06
    [token
    0.06
     illegally
    0.06
    _mo
    0.06
     Dani
    0.06
     zih
    0.06
     Slut
    0.06
    мов
    0.06
    Act Density 0.019%

    No Known Activations