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

    Neuronpedia

    INDEX
    Explanations

    questions asking what something is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     बेहद
    0.99
     youngsters
    0.99
     slated
    0.95
     revamped
    0.93
     revamp
    0.87
     제작
    0.87
     lavish
    0.86
     بشأن
    0.86
     young
    0.85
     superbly
    0.85
    POSITIVE LOGITS
     polynomial
    1.93
    Polynomial
    1.76
    polynomial
    1.68
     Polynomial
    1.67
     polynomials
    1.65
     covariance
    1.61
     quadratic
    1.59
     algebraic
    1.50
     enthalpy
    1.49
     Euclidean
    1.49
    Act Density 0.618%

    No Known Activations