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

    Neuronpedia

    INDEX
    Explanations

    lists and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phút
    -0.06
    _km
    -0.06
    iga
    -0.06
    Nu
    -0.06
    _offset
    -0.06
     root
    -0.06
    symbols
    -0.06
     Maker
    -0.06
     TICK
    -0.06
    queeze
    -0.06
    POSITIVE LOGITS
     Vari
    0.08
     Volley
    0.07
    faith
    0.07
    러리
    0.07
    ozor
    0.06
     =",
    0.06
    _Form
    0.06
     sailor
    0.06
    REQUIRED
    0.06
     Bí
    0.06
    Act Density 0.008%

    No Known Activations