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

    Neuronpedia

    INDEX
    Explanations

    coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лот
    -0.07
    =E
    -0.07
     blended
    -0.07
     Mandela
    -0.07
    (statement
    -0.07
    旦
    -0.07
     spirits
    -0.06
    ongoose
    -0.06
    	Vec
    -0.06
    よ
    -0.06
    POSITIVE LOGITS
    阅
    0.06
    _plane
    0.06
    议
    0.06
     barring
    0.06
    шь
    0.06
    _over
    0.06
    ()='
    0.06
    *size
    0.06
     ок
    0.06
    sam
    0.06
    Act Density 0.254%

    No Known Activations