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

    Neuronpedia

    INDEX
    Explanations

    enthusiasts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    、あ
    -0.07
     apo
    -0.07
    iê
    -0.07
    "For
    -0.06
     prezident
    -0.06
    vetica
    -0.06
    prü
    -0.06
    talya
    -0.06
     supermarkets
    -0.06
    cích
    -0.06
    POSITIVE LOGITS
     enthusiasts
    0.11
     enthusiast
    0.10
     grâce
    0.07
     lover
    0.07
     Durant
    0.06
     Tribune
    0.06
     Amateur
    0.06
    .Never
    0.06
     users
    0.06
    间
    0.06
    Act Density 0.013%

    No Known Activations