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

    Neuronpedia

    INDEX
    Explanations

    stringent requirements, comprehensive choice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    0.97
    E
    0.96
    C
    0.95
    ATION
    0.88
    n
    0.88
    IVITY
    0.87
    ната
    0.87
    이니
    0.85
    ن
    0.85
    R
    0.83
    POSITIVE LOGITS
    .${
    1.05
     for
    1.02
    \".
    0.98
    .}$
    0.95
    .\"
    0.94
    .";
    0.92
    .].
    0.91
    .​​
    0.91
    .。
    0.89
    .
    0.89
    Act Density 0.502%

    No Known Activations