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

    Neuronpedia

    INDEX
    Explanations

    Need for a solution

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     given
    -0.08
    Diamond
    -0.07
    鹃
    -0.07
    墼
    -0.07
    专人
    -0.07
    agger
    -0.07
     ideal
    -0.07
    }<
    -0.06
    BS
    -0.06
     endorse
    -0.06
    POSITIVE LOGITS
    -leading
    0.07
    _FIRE
    0.07
     scrambled
    0.07
    損害
    0.07
    stdlib
    0.07
     hủy
    0.07
    _have
    0.07
    -Line
    0.07
    ([...
    0.07
    лежа
    0.07
    Act Density 0.078%

    No Known Activations