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

    Neuronpedia

    INDEX
    Explanations

    css classes md sm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BleStatus
    0.46
    atap
    0.42
    libp
    0.41
    ymmetry
    0.41
    acterial
    0.40
    ரைப்
    0.40
    ArrayBox
    0.40
    拁
    0.39
    .|__
    0.38
    <unused206>
    0.38
    POSITIVE LOGITS
     six
    0.49
    t
    0.49
     three
    0.47
     one
    0.46
     eight
    0.46
     four
    0.45
     part
    0.45
    six
    0.45
     that
    0.43
     small
    0.43
    Act Density 0.002%

    No Known Activations