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

    Neuronpedia

    INDEX
    Explanations

    document title structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     नि
    0.37
    :‏
    0.37
    স্ত্রী
    0.36
    ่
    0.36
     shilling
    0.35
     scent
    0.35
     strip
    0.34
     जमी
    0.34
    ˹
    0.34
     entity
    0.34
    POSITIVE LOGITS
     entornos
    0.41
     Link
    0.38
    క్క
    0.38
    cosh
    0.38
     گئے
    0.37
     Kao
    0.37
     enthalpy
    0.37
     tâ
    0.37
     lingue
    0.37
    Prox
    0.36
    Act Density 0.003%

    No Known Activations