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

    Neuronpedia

    INDEX
    Explanations

    trying

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ba
    -0.07
    	Print
    -0.06
     terrace
    -0.06
    氏
    -0.06
     fibr
    -0.06
     PA
    -0.06
     dusk
    -0.06
    Birth
    -0.06
    ipient
    -0.06
     Adri
    -0.06
    POSITIVE LOGITS
     rozwiąz
    0.07
     חדש
    0.07
    可以选择
    0.07
    _else
    0.07
     החדש
    0.07
     יכול
    0.07
    铳
    0.07
    实体经济
    0.07
    甚至是
    0.06
    ળ
    0.06
    Act Density 0.002%

    No Known Activations