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

    Neuronpedia

    INDEX
    Explanations

    (empty string)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    聖
    -0.07
     ряд
    -0.07
    ім
    -0.07
     ам
    -0.07
     Gam
    -0.07
     hiding
    -0.06
     Coron
    -0.06
    анням
    -0.06
    린
    -0.06
    -double
    -0.06
    POSITIVE LOGITS
     olab
    0.07
    _FILENO
    0.06
    opyright
    0.06
    _ij
    0.06
     Skinner
    0.06
    retain
    0.06
    _E
    0.06
    purpose
    0.06
    variables
    0.06
    JV
    0.06
    Act Density 0.033%

    No Known Activations