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

    Neuronpedia

    INDEX
    Explanations

    wrap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    930
    -0.07
     %=
    -0.07
     possesses
    -0.07
     ela
    -0.07
    أة
    -0.06
    534
    -0.06
    Hugh
    -0.06
     fixation
    -0.06
    912
    -0.06
    _finder
    -0.06
    POSITIVE LOGITS
     intellectually
    0.08
    inished
    0.07
     châu
    0.07
     ganze
    0.07
    iguiente
    0.07
     غ
    0.07
    cripcion
    0.07
    .Classes
    0.06
    ılmıştır
    0.06
    �
    0.06
    Act Density 0.025%

    No Known Activations