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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("/",
    -0.07
    Gem
    -0.06
    represented
    -0.06
     rookies
    -0.06
    _equ
    -0.06
    _sum
    -0.06
     Suspension
    -0.06
     яку
    -0.06
     khách
    -0.06
    .urlopen
    -0.06
    POSITIVE LOGITS
     wrapped
    0.07
     obviously
    0.06
     Collabor
    0.06
     ли
    0.06
    cha
    0.06
    协
    0.06
     د
    0.06
    random
    0.06
     lubric
    0.06
    
    0.06
    Act Density 0.065%

    No Known Activations