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

    Neuronpedia

    INDEX
    Explanations

    testing and "Ribbit?"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    0.48
    امج
    0.46
    ో
    0.46
    реа
    0.45
    ಹ
    0.45
    吳
    0.44
     convenient
    0.43
    Conven
    0.43
    ρά
    0.42
    ріа
    0.42
    POSITIVE LOGITS
     bertahan
    0.52
    chrift
    0.49
     atenção
    0.46
     atención
    0.45
    iyah
    0.45
     pide
    0.45
     જવાબ
    0.44
    lerini
    0.44
    ulkan
    0.44
    ável
    0.44
    Act Density 0.000%

    No Known Activations