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

    Neuronpedia

    INDEX
    Explanations

    lists and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lifespan
    -0.07
    _shape
    -0.06
     invert
    -0.06
    shield
    -0.06
     outbreaks
    -0.06
    사진
    -0.06
    ‌شوند
    -0.06
    :g
    -0.06
    _Show
    -0.06
     Helper
    -0.06
    POSITIVE LOGITS
    Ab
    0.07
    BUY
    0.07
    铁
    0.07
     tzv
    0.07
    ITLE
    0.06
    kerja
    0.06
    	esc
    0.06
    ités
    0.06
     GLES
    0.06
     dầu
    0.06
    Act Density 0.080%

    No Known Activations