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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	scale
    -0.07
    采用
    -0.07
    ,const
    -0.07
    .ft
    -0.07
    crm
    -0.07
    please
    -0.06
    ight
    -0.06
    el
    -0.06
    _PE
    -0.06
     JV
    -0.06
    POSITIVE LOGITS
    崇拜
    0.07
    _RW
    0.07
    ウィ
    0.06
    ThanOr
    0.06
     Mot
    0.06
     twórc
    0.06
     מלא
    0.06
     الو
    0.06
    ⫸
    0.06
    Workers
    0.06
    Act Density 0.154%

    No Known Activations