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

    Neuronpedia

    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Brewing
    -0.07
     Marr
    -0.06
    ёр
    -0.06
     Hiro
    -0.06
    _long
    -0.06
    -corner
    -0.06
     Mé
    -0.06
     Tricks
    -0.06
     Cer
    -0.06
     odio
    -0.06
    POSITIVE LOGITS
     yaparak
    0.07
    ulen
    0.07
    =\"$
    0.07
    //================================================================
    0.07
     vua
    0.07
     natuur
    0.07
     charity
    0.07
    vars
    0.06
     yandan
    0.06
    VAS
    0.06
    Act Density 0.005%

    No Known Activations