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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    phem
    -0.07
     narrowed
    -0.06
     HOR
    -0.06
     sac
    -0.06
     оці
    -0.06
     nâng
    -0.06
    JPEG
    -0.06
    -mask
    -0.06
    AREN
    -0.06
     derecho
    -0.06
    POSITIVE LOGITS
    _controls
    0.07
     from
    0.07
    ',//
    0.06
     completamente
    0.06
     constitu
    0.06
     *</
    0.06
    ');");↵
    0.06
     Aur
    0.06
    riendly
    0.06
    ::::::::::::::::
    0.06
    Act Density 0.007%

    No Known Activations