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

    Neuronpedia

    INDEX
    Explanations

    different options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    方程
    0.48
     equation
    0.43
    するために
    0.41
     equations
    0.41
    Equation
    0.40
     Equation
    0.38
     समीकरण
    0.38
    Equations
    0.38
    atória
    0.38
    eqnarray
    0.37
    POSITIVE LOGITS
     डिफरेंट
    0.41
    individual
    0.41
     sundry
    0.39
    晎
    0.39
    異なる
    0.37
     künstler
    0.37
    也可
    0.37
    izare
    0.36
    サービスの
    0.35
    פקי
    0.35
    Act Density 0.000%

    No Known Activations