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

    Neuronpedia

    INDEX
    Explanations

    add functionality or features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    );
    1.93
     abiert
    1.88
     cauliflower
    1.84
    ங்கிணை
    1.80
    ())));
    1.80
     És
    1.80
    )))
    1.77
    )
    1.77
     underestimates
    1.74
    কার
    1.71
    POSITIVE LOGITS
    itionally
    2.06
    itrile
    2.03
    n
    2.02
    b
    1.94
    itively
    1.91
    d
    1.88
    ul
    1.80
    เสริม
    1.77
    em
    1.76
    ere
    1.73
    Act Density 0.718%

    No Known Activations