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

    Neuronpedia

    INDEX
    Explanations

    delta

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hav
    -0.07
    {
    -0.07
     næ
    -0.07
    -loading
    -0.06
     خاص
    -0.06
    eper
    -0.06
    -master
    -0.06
    스테
    -0.06
    _m
    -0.06
    -m
    -0.06
    POSITIVE LOGITS
     Worcester
    0.07
    ीकरण
    0.06
     Dahl
    0.06
     Clean
    0.06
    kan
    0.06
    939
    0.06
    ILI
    0.06
     Teddy
    0.06
     scrape
    0.06
    Jennifer
    0.06
    Act Density 0.000%

    No Known Activations