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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    istribution
    -0.07
    desktop
    -0.07
    straction
    -0.06
    .wallet
    -0.06
     Yue
    -0.06
     optic
    -0.06
    цвет
    -0.06
    _transition
    -0.06
    kills
    -0.06
     interpreter
    -0.06
    POSITIVE LOGITS
    ़्
    0.07
     Brisbane
    0.07
     Jeremy
    0.07
     Honest
    0.06
     arbitrarily
    0.06
     */;↵
    0.06
    μπο
    0.06
    Jimmy
    0.06
     arrive
    0.06
     Capitals
    0.06
    Act Density 0.033%

    No Known Activations