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

    Neuronpedia

    INDEX
    Explanations

    years and releases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     serpent
    -0.07
    ション
    -0.07
     Io
    -0.07
     IMessage
    -0.07
    اجر
    -0.07
    USH
    -0.06
    RIPT
    -0.06
    M
    -0.06
     sulf
    -0.06
     ENT
    -0.06
    POSITIVE LOGITS
     notices
    0.06
     rentals
    0.06
    isha
    0.06
    και
    0.06
     ثلاث
    0.05
     lesen
    0.05
    .getBean
    0.05
     sourceMapping
    0.05
     hust
    0.05
     wears
    0.05
    Act Density 0.147%

    No Known Activations