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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ಆ
    -0.08
    畢業
    -0.08
    hib
    -0.07
     fot
    -0.07
    sorry
    -0.07
     concentrating
    -0.07
     Rico
    -0.07
    eor
    -0.07
     Yo
    -0.07
    هو
    -0.07
    POSITIVE LOGITS
     option
    0.07
     uid
    0.07
    多くの
    0.07
     launched
    0.07
     созд
    0.07
    LineEdit
    0.07
    잇
    0.07
    :@""
    0.07
    含量
    0.07
     options
    0.07
    Act Density 0.002%

    No Known Activations