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
     Shades
    -0.07
    adors
    -0.06
    issors
    -0.06
     dağı
    -0.06
    /****************************************
    -0.06
     ان
    -0.06
    erc
    -0.06
    _);
↵
    -0.06
    ountries
    -0.06
    	ERROR
    -0.06
    POSITIVE LOGITS
    spm
    0.07
     captivating
    0.07
    .RELATED
    0.07
    nummer
    0.07
     cinsel
    0.06
    (schema
    0.06
    kat
    0.06
    _numer
    0.06
     Elite
    0.06
     особливо
    0.06
    Act Density 0.000%

    No Known Activations