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

    Neuronpedia

    INDEX
    Explanations

    reciprocal skill exchange

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мета
    0.48
     reales
    0.47
    intis
    0.45
     menggambarkan
    0.45
     NOx
    0.45
     λ
    0.44
     simulates
    0.44
     why
    0.44
     क्यों
    0.44
     পতাকা
    0.44
    POSITIVE LOGITS
    败
    0.45
    ManagerState
    0.44
    ണാ
    0.43
    初心
    0.43
     bete
    0.42
    Loving
    0.42
    那里
    0.41
     Loving
    0.40
     Forman
    0.40
    نات
    0.40
    Act Density 0.004%

    No Known Activations