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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attractions
    -0.07
     Anton
    -0.07
     NotSupportedException
    -0.06
    ADF
    -0.06
     Separate
    -0.06
    	unsigned
    -0.06
    раниц
    -0.06
    Drivers
    -0.06
    سین
    -0.06
    컬
    -0.06
    POSITIVE LOGITS
    }',↵
    0.07
     Wanna
    0.06
    Perm
    0.06
     pars
    0.06
    ök
    0.06
    شب
    0.06
    ห
    0.06
    enderit
    0.06
    _node
    0.06
    logg
    0.06
    Act Density 0.000%

    No Known Activations