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

    Neuronpedia

    INDEX
    Explanations

    en

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    레스
    -0.07
    :&
    -0.07
    °E
    -0.06
    ()">↵
    -0.06
    userdata
    -0.06
    gewater
    -0.06
     prezident
    -0.06
    =id
    -0.06
     ORD
    -0.06
     P
    -0.06
    POSITIVE LOGITS
    en
    0.07
     Obama
    0.07
    _factors
    0.07
    .replace
    0.07
     injecting
    0.07
    licated
    0.07
    leme
    0.06
     Pierce
    0.06
    	queue
    0.06
    慎
    0.06
    Act Density 0.002%

    No Known Activations