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

    Neuronpedia

    INDEX
    Explanations

    b

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     없어
    -0.07
     tenemos
    -0.06
     jinak
    -0.06
     MESSAGE
    -0.06
    nginx
    -0.06
    εω
    -0.06
    нение
    -0.06
    UED
    -0.06
     Gobierno
    -0.06
     Corbyn
    -0.06
    POSITIVE LOGITS
     rect
    0.07
    $a
    0.06
     Infer
    0.06
     utilizing
    0.06
    433
    0.06
    831
    0.06
    Sha
    0.06
     whirl
    0.06
     fostering
    0.06
    海
    0.06
    Act Density 0.007%

    No Known Activations