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

    Neuronpedia

    INDEX
    Explanations

    email, time, gender, identity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     psal
    0.49
    blusas
    0.43
     expectancy
    0.43
    ěz
    0.42
     পালন
    0.41
     agglomer
    0.41
    ងឺ
    0.40
    [_
    0.40
    brano
    0.40
    读者
    0.40
    POSITIVE LOGITS
     Poly
    0.41
     Substitute
    0.41
     Locked
    0.40
    Poly
    0.38
     Solve
    0.38
     Th
    0.38
    Locked
    0.38
     Kay
    0.37
    locked
    0.37
     D
    0.37
    Act Density 0.000%

    No Known Activations