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

    Neuronpedia

    INDEX
    Explanations

    data operations and errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zu
    0.82
    )}{
    0.71
     James
    0.68
    裤
    0.66
     Wars
    0.66
    LS
    0.65
    tek
    0.65
    褲
    0.65
    候选
    0.65
     tunnel
    0.65
    POSITIVE LOGITS
     move
    0.95
     measure
    0.89
    measures
    0.84
     medida
    0.82
     moves
    0.82
     measures
    0.81
     Measure
    0.79
     Moves
    0.77
     Move
    0.75
     Measures
    0.74
    Act Density 0.117%

    No Known Activations