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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    instancetype
    -0.07
    暑
    -0.07
     części
    -0.07
     intensified
    -0.07
    Drawable
    -0.07
    .Transparent
    -0.06
    	push
    -0.06
     exercício
    -0.06
    _Name
    -0.06
    ȩ
    -0.06
    POSITIVE LOGITS
    国家队
    0.08
    贝
    0.07
    .iteritems
    0.07
    JPEG
    0.07
    Jeff
    0.07
     naveg
    0.07
     integrity
    0.07
     bible
    0.06
    糵
    0.06
    给他
    0.06
    Act Density 0.047%

    No Known Activations