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

    Neuronpedia

    INDEX
    Explanations

    brain processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ेलकम
    0.52
     menjual
    0.51
     satış
    0.50
     prévoit
    0.49
     negócios
    0.49
    btnLogout
    0.49
    acariy
    0.48
     propriétaires
    0.48
     paiement
    0.48
     preços
    0.47
    POSITIVE LOGITS
    ↵
    0.64
    ↵↵
    0.54
     \
    0.54
     G
    0.48
     J
    0.48
     (-
    0.48
    },
    0.47
     moduli
    0.46
     pseud
    0.45
    .
    0.45
    Act Density 0.001%

    No Known Activations