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

    Neuronpedia

    INDEX
    Explanations

    potential future outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ploy
    1.21
     centralized
    1.09
     rumors
    1.06
    時候
    1.05
     tutkim
    1.05
     mädchen
    1.05
     retaliation
    1.04
     firsthand
    1.03
     postgraduate
    1.03
     gasto
    1.03
    POSITIVE LOGITS
    c
    1.54
    ك
    1.23
    Y
    1.19
    g
    1.14
    k
    1.13
    ס
    1.08
    si
    1.02
     своим
    1.00
    di
    0.96
    d
    0.96
    Act Density 0.261%

    No Known Activations