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

    Neuronpedia

    INDEX
    Explanations

    revenue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    証
    -0.06
     Prep
    -0.06
    лин
    -0.05
     rel
    -0.05
    _ports
    -0.05
     cognition
    -0.05
    .expr
    -0.05
     Violence
    -0.05
    .cd
    -0.05
    iado
    -0.05
    POSITIVE LOGITS
     Personally
    0.08
    andid
    0.07
     řid
    0.07
     Saw
    0.07
    (editor
    0.07
    	scope
    0.07
     Hopefully
    0.07
     ruining
    0.07
    /unit
    0.07
     @"↵
    0.07
    Act Density 0.064%

    No Known Activations