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

    Neuronpedia

    INDEX
    Explanations

    html structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     כך
    0.60
    [
    0.51
    ar
    0.50
     rans
    0.50
     appunto
    0.49
    ます
    0.48
     wording
    0.47
    perturb
    0.47
    ASTIC
    0.46
    ন
    0.46
    POSITIVE LOGITS
    к
    0.54
    rk
    0.53
    kN
    0.52
    ை
    0.51
     tern
    0.49
    )}+\
    0.49
    is
    0.48
    гийн
    0.47
    shopify
    0.47
    stmt
    0.47
    Act Density 2.693%

    No Known Activations