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

    Neuronpedia

    INDEX
    Explanations

    headings and summaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    0.51
    R
    0.47
    in
    0.47
    S
    0.45
     */
    0.44
    our
    0.44
    e
    0.43
    jur
    0.43
    y
    0.43
    an
    0.42
    POSITIVE LOGITS
    ڈیو
    0.45
     έχουν
    0.44
    ိုး
    0.43
    锕
    0.43
     encuentre
    0.43
     múlti
    0.41
     yatırım
    0.41
     पुरंदरे
    0.40
    শক্ত
    0.40
     Bảo
    0.40
    Act Density 0.001%

    No Known Activations