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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ogany
    -0.07
    evil
    -0.06
    ogan
    -0.06
    째
    -0.06
    属
    -0.06
    	rc
    -0.06
    "})
    -0.06
    /P
    -0.06
    нил
    -0.06
    .File
    -0.06
    POSITIVE LOGITS
     <?=$
    0.06
     Score
    0.06
    _ASS
    0.06
     alterations
    0.06
    ｢
    0.06
     Couch
    0.06
     regul
    0.06
     nicotine
    0.06
    秘
    0.06
    	esc
    0.06
    Act Density 0.057%

    No Known Activations