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

    Neuronpedia

    INDEX
    Explanations

    Filter

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    devices
    -0.08
     Emily
    -0.07
     Marl
    -0.07
    PyObject
    -0.07
    _ascii
    -0.07
    置身
    -0.07
    .Rem
    -0.07
    Structured
    -0.07
     Clifford
    -0.07
    סיס
    -0.07
    POSITIVE LOGITS
    了一遍
    0.07
    ᎑
    0.06
    &#
    0.06
    )++;↵
    0.06
    ),(
    0.06
     bey
    0.06
    ((↵
    0.06
    一同
    0.06
    >/<
    0.06
    ','
    0.06
    Act Density 0.001%

    No Known Activations