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

    Neuronpedia

    INDEX
    Explanations

    price, length, attack, iterate, always

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ASME
    0.79
     chamada
    0.77
    ")):
    0.75
     Freiheit
    0.75
    IA
    0.74
    Group
    0.73
    GER
    0.73
    NIA
    0.73
     BAC
    0.73
    ACG
    0.72
    POSITIVE LOGITS
    munition
    0.77
     生
    0.77
    tter
    0.76
     सब्जियों
    0.75
     fertilisers
    0.75
    ます
    0.74
    تها
    0.73
    ात
    0.71
    manship
    0.70
    mind
    0.70
    Act Density 0.004%

    No Known Activations