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

    Neuronpedia

    INDEX
    Explanations

    Scientific notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Feather
    -0.07
     Jab
    -0.07
     проблеми
    -0.06
     backend
    -0.06
     SALE
    -0.06
     Engineer
    -0.06
    arım
    -0.06
     cheerful
    -0.06
    )const
    -0.06
     Sok
    -0.06
    POSITIVE LOGITS
     anthology
    0.07
    ажд
    0.07
    leta
    0.07
    dling
    0.07
    Ast
    0.06
     flyer
    0.06
    uable
    0.06
     (<
    0.06
    onces
    0.06
    lease
    0.06
    Act Density 0.010%

    No Known Activations