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

    Neuronpedia

    INDEX
    Explanations

    official announcements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ensemble
    -0.07
     roll
    -0.06
     switches
    -0.06
    امین
    -0.06
     billions
    -0.06
     momentum
    -0.06
     inference
    -0.06
    JSON
    -0.06
     ransom
    -0.06
    кі
    -0.06
    POSITIVE LOGITS
    .FormattingEnabled
    0.07
     FirebaseDatabase
    0.07
    Firebase
    0.07
    ponsored
    0.07
     술
    0.07
    #g
    0.07
    .Flag
    0.06
    [S
    0.06
     beloved
    0.06
    圣
    0.06
    Act Density 0.080%

    No Known Activations