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

    Neuronpedia

    INDEX
    Explanations

    approved

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    몰
    -0.07
    _expected
    -0.07
    徂
    -0.07
    到场
    -0.07
    :]↵↵
    -0.07
    的事实
    -0.06
    	insert
    -0.06
    	Event
    -0.06
    industry
    -0.06
    成功
    -0.06
    POSITIVE LOGITS
     Kod
    0.07
     coat
    0.07
    灯光
    0.07
    ocate
    0.07
     Jacob
    0.06
    educ
    0.06
     skateboard
    0.06
     shaded
    0.06
    _COD
    0.06
    hat
    0.06
    Act Density 0.033%

    No Known Activations