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

    Neuronpedia

    INDEX
    Explanations

    inhale

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ège
    -0.08
     arrange
    -0.07
     Treasure
    -0.07
    Atomic
    -0.07
     pockets
    -0.07
    agner
    -0.07
     budget
    -0.07
    Budget
    -0.07
    หลากหลาย
    -0.07
    ellites
    -0.07
    POSITIVE LOGITS
     __(
    0.07
    (accounts
    0.07
    뻤
    0.07
    _hello
    0.07
     brawl
    0.06
    :expr
    0.06
     وأشار
    0.06
    .ContainsKey
    0.06
     adultery
    0.06
    ܩ
    0.06
    Act Density 0.005%

    No Known Activations