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

    Neuronpedia

    INDEX
    Explanations

    scheduler; include (

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ad
    0.55
    an
    0.52
    жээ
    0.51
    s
    0.51
    est
    0.50
    uot
    0.50
    ied
    0.50
    ದ
    0.50
    라고
    0.49
    ellä
    0.49
    POSITIVE LOGITS
    ме
    0.55
    AR
    0.54
    挀
    0.53
    EM
    0.52
    OR
    0.50
    OP
    0.49
     educação
    0.49
    OM
    0.48
    Photograph
    0.47
     ആണ്
    0.47
    Act Density 0.000%

    No Known Activations