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

    Neuronpedia

    INDEX
    Explanations

    Life

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    细致
    -0.08
     comenz
    -0.07
    .easing
    -0.07
    การทำงาน
    -0.07
    otoxic
    -0.07
     electrical
    -0.07
     Bruce
    -0.07
     invasive
    -0.07
     parachute
    -0.07
     Oliv
    -0.07
    POSITIVE LOGITS
    imps
    0.07
    ler
    0.07
    icators
    0.07
     trial
    0.07
    body
    0.07
    irt
    0.07
              
↵
    0.07
    izer
    0.07
     favoured
    0.07
    erging
    0.07
    Act Density 0.008%

    No Known Activations