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

    Neuronpedia

    INDEX
    Explanations

    enhance, reduce, maximize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GAS
    0.95
     danni
    0.95
    {
    0.92
    GET
    0.91
    Attempt
    0.86
    že
    0.84
    ST
    0.83
     FROM
    0.83
    Getter
    0.82
    ON
    0.81
    POSITIVE LOGITS
    न
    1.38
    रिया
    1.18
    ত্ব
    1.13
    ल
    1.13
    री
    1.10
    缚
    1.05
    नो
    1.04
    べて
    1.04
    क
    1.04
    د
    1.03
    Act Density 0.155%

    No Known Activations