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

    Neuronpedia

    INDEX
    Explanations

    range

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     creativity
    -0.07
    ᆡ
    -0.07
     Edmund
    -0.07
    Sans
    -0.07
    etu
    -0.07
     nex
    -0.06
     Promo
    -0.06
    preview
    -0.06
     propensity
    -0.06
    Sum
    -0.06
    POSITIVE LOGITS
    投标
    0.07
    itals
    0.07
     alkal
    0.07
    or
    0.07
    ccoli
    0.07
     ounces
    0.07
    onas
    0.07
     Offering
    0.06
    buffers
    0.06
    icle
    0.06
    Act Density 0.084%

    No Known Activations