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

    Neuronpedia

    INDEX
    Explanations

    affine, projective, project

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    1.85
    b
    1.78
    ir
    1.59
    id
    1.58
    ik
    1.55
    it
    1.53
    s
    1.52
    p
    1.48
    al
    1.45
    de
    1.45
    POSITIVE LOGITS
     contenuti
    1.29
     rozwiąz
    1.27
     macchina
    1.17
     direttore
    1.16
     contenuto
    1.15
    dır
    1.14
     storica
    1.13
     convivial
    1.13
     culturale
    1.12
     கட்சி
    1.10
    Act Density 0.008%

    No Known Activations