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

    Neuronpedia

    INDEX
    Explanations

    Intel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    工具
    -0.07
    alarında
    -0.06
     phóng
    -0.06
     процед
    -0.06
     pregunta
    -0.06
     revis
    -0.06
    avid
    -0.06
     görmek
    -0.06
    adoop
    -0.06
    dete
    -0.06
    POSITIVE LOGITS
     normal
    0.07
    endregion
    0.07
     affluent
    0.07
     advertised
    0.07
     responding
    0.06
     father
    0.06
     remembers
    0.06
    .setInput
    0.06
     democratic
    0.06
     Dell
    0.06
    Act Density 0.001%

    No Known Activations