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

    Neuronpedia

    INDEX
    Explanations

    hashtags with subsequent words

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

    # or * followed by list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.86
     vijf
    0.70
     ৮
    0.65
    ých
    0.61
     oito
    0.61
     be
    0.59
    8
    0.58
    開始
    0.58
     cinq
    0.58
     是
    0.57
    POSITIVE LOGITS
    an
    1.02
    u
    0.89
    ون
    0.82
    h
    0.82
    ان
    0.80
    ח
    0.80
    f
    0.79
    er
    0.79
    g
    0.79
    ா
    0.79
    Act Density 0.004%

    No Known Activations