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

    Neuronpedia

    INDEX
    Explanations

    selected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ņi
    1.21
    ,{\
    1.12
    ètement
    1.12
    .$(
    1.10
     relacionada
    1.10
     envolvendo
    1.09
    ارات
    1.08
    ুম
    1.06
    ডেল
    1.06
    flask
    1.04
    POSITIVE LOGITS
    为
    1.17
    la
    1.04
    tilde
    1.03
    lb
    1.01
    rained
    1.01
    lbl
    1.00
    జర్
    0.99
    lp
    0.99
    成为
    0.99
    larının
    0.98
    Act Density 0.000%

    No Known Activations