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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gift
    -0.08
    -defense
    -0.08
     forthcoming
    -0.07
     unleash
    -0.07
     hindi
    -0.06
    swift
    -0.06
     vite
    -0.06
    /an
    -0.06
    💨
    -0.06
     AF
    -0.06
    POSITIVE LOGITS
     tecrü
    0.08
    atic
    0.07
    ือ
    0.07
    퓲
    0.07
     Possibly
    0.07
     coats
    0.06
     layers
    0.06
    typeorm
    0.06
     Эт
    0.06
    :@""
    0.06
    Act Density 0.002%

    No Known Activations