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

    Neuronpedia

    INDEX
    Explanations

    introducing a comparison table

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hline
    0.98
     row
    0.88
    row
    0.87
    multicolumn
    0.81
    ――――
    0.78
     rows
    0.77
    linha
    0.76
    －－
    0.74
     classified
    0.74
     Row
    0.73
    POSITIVE LOGITS
     |
    1.34
    |
    1.15
    ,|
    0.84
     (|
    0.81
     $|
    0.81
     |_
    0.80
    |".
    0.78
    ڙ
    0.78
     |\
    0.77
    ｜
    0.77
    Act Density 0.010%

    No Known Activations