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

    Neuronpedia

    INDEX
    Explanations

    Code and file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ptr
    -0.07
     adopts
    -0.07
    比較
    -0.07
     supra
    -0.07
    贷
    -0.07
     موقع
    -0.07
    	pt
    -0.07
     mayor
    -0.07
     between
    -0.07
     presidente
    -0.07
    POSITIVE LOGITS
    ETING
    0.07
    \Model
    0.07
    江县
    0.07
    正しい
    0.07
    Ⱥ
    0.07
    檫
    0.06
    徂
    0.06
    دولة
    0.06
    침
    0.06
    㽏
    0.06
    Act Density 0.170%

    No Known Activations