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

    Neuronpedia

    INDEX
    Explanations

    comma followed by at or surrounded

    np_acts-logits-general · gemini-2.5-flash-lite

    dates and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ig
    0.59
    i
    0.57
    gående
    0.52
    ième
    0.52
    em
    0.51
    embourg
    0.51
     excès
    0.50
    er
    0.50
    ib
    0.50
    tons
    0.50
    POSITIVE LOGITS
    は
    0.64
     be
    0.58
    이트
    0.54
    은
    0.52
    も
    0.49
    ロード
    0.48
    в
    0.48
    は約
    0.48
    бычно
    0.47
    曈
    0.46
    Act Density 0.001%

    No Known Activations