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

    Neuronpedia

    INDEX
    Explanations

    projects and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.46
    ו
    0.43
    w
    0.41
    re
    0.41
     on
    0.41
    et
    0.40
    at
    0.39
    an
    0.38
    as
    0.38
    v
    0.38
    POSITIVE LOGITS
    ತ್ನ
    0.36
     técnica
    0.35
     odnosno
    0.35
     identificado
    0.35
     requête
    0.34
     energética
    0.34
     solicitado
    0.34
    ９
    0.34
     effectués
    0.34
     tantôt
    0.34
    Act Density 0.266%

    No Known Activations