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

    Neuronpedia

    INDEX
    Explanations

    causal language modeling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pu
    0.40
     calculated
    0.38
    imated
    0.38
    calculated
    0.38
    bure
    0.38
    alone
    0.38
    calcul
    0.37
    bala
    0.36
    readers
    0.36
    foot
    0.36
    POSITIVE LOGITS
    擲
    0.43
    тков
    0.39
     дома
    0.37
    тел
    0.37
     gemak
    0.37
     Inu
    0.36
     Lam
    0.36
     emocional
    0.36
    HeaderParams
    0.36
    ;|
    0.36
    Act Density 0.000%

    No Known Activations