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

    Neuronpedia

    INDEX
    Explanations

    css code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dah
    -0.08
    تع
    -0.07
    	HX
    -0.07
     Goth
    -0.07
    _break
    -0.07
     parametros
    -0.06
    اى
    -0.06
     documentos
    -0.06
     hroz
    -0.06
    meyi
    -0.06
    POSITIVE LOGITS
     Zac
    0.06
     fanc
    0.06
    grammar
    0.06
    верд
    0.06
     Ý
    0.06
     cf
    0.06
    백
    0.06
    าประ
    0.06
     Sind
    0.05
    arrival
    0.05
    Act Density 0.015%

    No Known Activations