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

    Neuronpedia

    INDEX
    Explanations

    Privacy promises

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Charset
    -0.08
    }else
    -0.07
    WORDS
    -0.07
     Biol
    -0.07
    ])==
    -0.06
    控制
    -0.06
     GAR
    -0.06
    شنبه
    -0.06
    ANNER
    -0.06
    当然
    -0.06
    POSITIVE LOGITS
     baktı
    0.08
    饭
    0.07
    stagram
    0.07
    (eventName
    0.06
    _candidates
    0.06
    _DELETED
    0.06
    olid
    0.06
    	pid
    0.06
    =id
    0.06
    polator
    0.06
    Act Density 0.005%

    No Known Activations