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

    Neuronpedia

    INDEX
    Explanations

    false

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forte
    -0.07
     Blank
    -0.06
    oggled
    -0.06
     파
    -0.06
    ...')↵
    -0.06
    írk
    -0.06
    玻璃
    -0.06
     silver
    -0.06
     κου
    -0.06
    立ち
    -0.06
    POSITIVE LOGITS
     šest
    0.07
    Servers
    0.07
    ness
    0.07
    }=
    0.07
    ponsored
    0.07
     devastation
    0.06
     người
    0.06
     апр
    0.06
    optic
    0.06
     dob
    0.06
    Act Density 0.000%

    No Known Activations