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

    Neuronpedia

    INDEX
    Explanations

    compiling data or listing items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Give
    0.86
    Giving
    0.86
    giving
    0.83
    Restore
    0.78
    rest
    0.74
    fold
    0.74
    Notice
    0.73
    give
    0.71
    Mang
    0.69
    HS
    0.69
    POSITIVE LOGITS
    ᴥ
    1.05
    PLEMENT
    1.03
     pwm
    1.01
    𐰇
    0.98
     interracial
    0.95
     suis
    0.94
    <unused43>
    0.94
     olie
    0.93
     haki
    0.93
     korea
    0.93
    Act Density 0.000%

    No Known Activations