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

    Neuronpedia

    INDEX
    Explanations

    listing items and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tobago
    0.51
    ्राफी
    0.50
    Ր
    0.47
    했다
    0.44
     scourge
    0.44
     ಸಮಸ್ಯ
    0.44
     !}\
    0.44
    तला
    0.44
     unjust
    0.43
    ປັນ
    0.43
    POSITIVE LOGITS
     from
    0.63
    G
    0.49
     $
    0.48
     Ultra
    0.48
     pre
    0.48
    W
    0.48
     From
    0.46
     Maximus
    0.46
    p
    0.46
     Green
    0.46
    Act Density 0.000%

    No Known Activations