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

    Neuronpedia

    INDEX
    Explanations

    struggling or attempting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    k
    0.42
    ks
    0.41
    ;
    0.41
    7
    0.40
     although
    0.39
     discussed
    0.38
    ausea
    0.38
    l
    0.38
    1
    0.38
    2
    0.38
    POSITIVE LOGITS
     మాత్రం
    0.51
     appunto
    0.46
     এতটা
    0.45
     ovako
    0.41
     właśnie
    0.40
     столь
    0.40
     tantos
    0.38
    부가
    0.37
     چنین
    0.37
    這麼
    0.36
    Act Density 0.019%

    No Known Activations