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

    Neuronpedia

    INDEX
    Explanations

    algebraic fields

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FID
    0.80
    фи
    0.76
    öst
    0.75
    ಫ
    0.75
    чета
    0.75
    ಜು
    0.75
     सिक
    0.73
    F
    0.72
    כות
    0.72
    attup
    0.72
    POSITIVE LOGITS
     Zeitung
    0.89
     Modulation
    0.74
     moléculas
    0.72
     Chameleon
    0.71
     realizzato
    0.71
     Geträn
    0.70
     Convolution
    0.70
     Gesture
    0.70
     Grocery
    0.70
    мулятор
    0.69
    Act Density 0.000%

    No Known Activations