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

    Neuronpedia

    INDEX
    Explanations

    card game hands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ology
    0.61
    -
    0.57
    Salary
    0.55
    ared
    0.52
    Salon
    0.52
    ﺖ
    0.52
    Heart
    0.50
    ales
    0.49
    hana
    0.49
    Sink
    0.49
    POSITIVE LOGITS
    叭
    0.56
     Aş
    0.55
     probabil
    0.54
     v
    0.53
     for
    0.52
     gols
    0.52
     traits
    0.51
    ې
    0.51
     binaries
    0.50
    ش
    0.50
    Act Density 0.001%

    No Known Activations