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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Axes
    -0.06
     udál
    -0.06
     offsetX
    -0.06
    ↵↵
    -0.06
    ("""↵
    -0.06
    .getType
    -0.06
     싸
    -0.06
     бак
    -0.06
    appen
    -0.06
     Федера
    -0.06
    POSITIVE LOGITS
     only
    0.09
    Only
    0.08
     Only
    0.07
    only
    0.07
    ONLY
    0.07
    _ONLY
    0.07
     solely
    0.07
    -only
    0.07
     từ
    0.07
    _only
    0.06
    Act Density 0.017%

    No Known Activations