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

    Neuronpedia

    INDEX
    Explanations

    grid layout terms like columnspan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Telemetry
    0.44
    тала
    0.42
    过
    0.42
    甯
    0.42
    ينية
    0.41
    ኅ
    0.40
    𝓖
    0.39
    тные
    0.39
    ède
    0.39
    芋
    0.39
    POSITIVE LOGITS
     colspan
    0.77
     rowspan
    0.67
     columnspan
    0.65
     cos
    0.64
    colspan
    0.61
     CO
    0.60
    multicolumn
    0.59
     kos
    0.51
     width
    0.50
    cos
    0.50
    Act Density 0.000%

    No Known Activations