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

    Neuronpedia

    INDEX
    Explanations

    numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zel
    -0.08
     terminology
    -0.08
     Thema
    -0.07
    正
    -0.07
    zele
    -0.07
    grado
    -0.07
     perfeitamente
    -0.07
     сир
    -0.07
     dane
    -0.07
    ிருந்து
    -0.07
    POSITIVE LOGITS
    الأ
    0.09
     pasted
    0.08
     bals
    0.08
    Provider
    0.07
     burnt
    0.07
     threaded
    0.07
    óvil
    0.07
     МО
    0.07
    Containers
    0.07
     discontinued
    0.07
    Act Density 0.267%

    No Known Activations