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

    Neuronpedia

    INDEX
    Explanations

    calculate or find

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    虺
    0.85
    m
    0.84
     entdeck
    0.82
     tecl
    0.79
     geschaffen
    0.79
    crom
    0.78
     cursing
    0.77
    ร่วม
    0.77
     imperfection
    0.76
    mär
    0.75
    POSITIVE LOGITS
    Calculate
    0.87
    जल
    0.75
    calculate
    0.71
    IndexOf
    0.71
    Nearest
    0.69
     у
    0.68
    Estimate
    0.66
    Generate
    0.65
    че
    0.64
    োদ্ধ
    0.63
    Act Density 0.361%

    No Known Activations