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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ANDROID
    -0.09
    ucken
    -0.08
     Banking
    -0.08
    bal
    -0.08
     IGN
    -0.08
    كد
    -0.07
     xls
    -0.07
     Vib
    -0.07
     Vij
    -0.07
    قدر
    -0.07
    POSITIVE LOGITS
    	from
    0.07
    _RM
    0.07
     elemento
    0.06
    ("<
    0.06
    ﬤ
    0.06
     Neue
    0.06
    临
    0.06
     vistas
    0.06
    ᩃ
    0.06
     premises
    0.06
    Act Density 0.001%

    No Known Activations