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

    Neuronpedia

    INDEX
    Explanations

    Underscore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bert
    -0.07
     губ
    -0.07
     stdout
    -0.07
    -device
    -0.07
     bậc
    -0.07
     algunos
    -0.07
     라이
    -0.07
     surv
    -0.07
     betray
    -0.07
     trois
    -0.06
    POSITIVE LOGITS
    .FindControl
    0.06
    经营
    0.06
     flap
    0.06
     posledních
    0.06
    ेण
    0.06
     Losing
    0.05
    _SANITIZE
    0.05
    
↵

↵
    0.05
     المهنة
    0.05
    .Restr
    0.05
    Act Density 0.006%

    No Known Activations