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

    Neuronpedia

    INDEX
    Explanations

    generator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tab
    -0.08
     Stad
    -0.07
    (al
    -0.07
     cab
    -0.07
    であ
    -0.06
     är
    -0.06
     бой
    -0.06
     브라
    -0.06
    .contacts
    -0.06
    ,e
    -0.06
    POSITIVE LOGITS
     generator
    0.07
    UREMENT
    0.07
    ॉट
    0.07
     Generator
    0.07
    ponsored
    0.07
     đặc
    0.07
     rumours
    0.06
     Harness
    0.06
    INI
    0.06
    ernel
    0.06
    Act Density 0.004%

    No Known Activations