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

    Neuronpedia

    INDEX
    Explanations

    company history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ‎#
    -0.07
    mail
    -0.06
     ties
    -0.06
    Beer
    -0.06
    /]
    -0.06
    pert
    -0.06
     firmware
    -0.06
     Arsenal
    -0.06
    MH
    -0.06
    UserCode
    -0.06
    POSITIVE LOGITS
    avored
    0.07
     Cable
    0.06
     informací
    0.06
    Setup
    0.06
    getContext
    0.06
     هفت
    0.06
    quiring
    0.06
    afka
    0.06
    probante
    0.06
    へと
    0.06
    Act Density 0.056%

    No Known Activations