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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stage
    -0.08
     oauth
    -0.07
     Garrett
    -0.07
    ClassNotFoundException
    -0.07
    dto
    -0.07
    abled
    -0.07
    мед
    -0.07
     HD
    -0.06
     Crypto
    -0.06
     Voyage
    -0.06
    POSITIVE LOGITS
    _WORDS
    0.07
     enormously
    0.07
    	expect
    0.07
    🥰
    0.07
    {};↵
    0.07
    (;
    0.07
    	writel
    0.07
    魉
    0.06
     basically
    0.06
     Indones
    0.06
    Act Density 0.003%

    No Known Activations