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

    Neuronpedia

    INDEX
    Explanations

    quarter to quarter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ایج
    0.71
     gauche
    0.56
     seguinte
    0.54
     graphique
    0.53
     pieds
    0.52
     sympathique
    0.52
     prácticamente
    0.51
     niż
    0.50
    ická
    0.50
     டை
    0.50
    POSITIVE LOGITS
     Payment
    0.48
    Payment
    0.47
    َهُ
    0.45
    ^{-\
    0.45
    tung
    0.44
    henburg
    0.44
    gin
    0.43
     Aladdin
    0.43
     SIL
    0.43
     Consequences
    0.43
    Act Density 0.000%

    No Known Activations