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

    Neuronpedia

    INDEX
    Explanations

    calculations and mathematical operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     szak
    0.88
    मतौर
    0.87
     früh
    0.84
     evita
    0.84
     laminate
    0.82
     Иногда
    0.82
     tranh
    0.81
     γιατί
    0.80
     Spine
    0.79
    0.79
    POSITIVE LOGITS
     billion
    0.84
     Calculator
    0.78
     Mathematics
    0.77
     mathematical
    0.75
    UTICAL
    0.75
    Calculate
    0.75
     dígitos
    0.74
     Mathematical
    0.74
     Calculate
    0.73
    calories
    0.73
    Act Density 0.001%

    No Known Activations