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

    Neuronpedia

    INDEX
    Explanations

    code and math questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     truncate
    -0.07
    Early
    -0.06
     italiani
    -0.06
     evacuation
    -0.06
     ağır
    -0.06
     Uz
    -0.06
    ία
    -0.06
     Piano
    -0.06
     limiting
    -0.06
    egrated
    -0.06
    POSITIVE LOGITS
    fortune
    0.06
    :Any
    0.06
    getto
    0.06
    etermine
    0.06
    "}↵↵
    0.06
     Maven
    0.06
     اليوم
    0.06
    	↵	↵
    0.06
     Rivera
    0.06
    _self
    0.06
    Act Density 0.002%

    No Known Activations