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

    Neuronpedia

    INDEX
    Explanations

    rows and columns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     advogado
    0.47
    طلاع
    0.46
     ناج
    0.42
     emprend
    0.41
     Sekret
    0.40
     العافيه
    0.40
     sponsoring
    0.39
    Attk
    0.39
    တင်
    0.39
     odborn
    0.39
    POSITIVE LOGITS
     row
    0.82
     Row
    0.75
    Row
    0.72
     rows
    0.71
    row
    0.63
    Rows
    0.62
     Rows
    0.59
    行
    0.58
     ROW
    0.54
     horizontal
    0.53
    Act Density 0.158%

    No Known Activations