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

    Neuronpedia

    INDEX
    Explanations

    AI model role

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Har
    0.70
    ڑوں
    0.67
    ված
    0.67
    miş
    0.66
    дары
    0.65
    Unknown
    0.63
    യും
    0.63
    icited
    0.62
    деся
    0.62
    作る
    0.62
    POSITIVE LOGITS
     model
    0.96
     role
    0.83
    model
    0.81
     LC
    0.79
     Л
    0.78
     problem
    0.77
     Role
    0.75
     program
    0.73
     ल
    0.73
     Model
    0.72
    Act Density 0.034%

    No Known Activations