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

    Neuronpedia

    INDEX
    Explanations

    Scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cousins
    -0.08
    フォ
    -0.08
    ıyord
    -0.07
    .fileName
    -0.06
    演练
    -0.06
    Patients
    -0.06
    checker
    -0.06
    setFont
    -0.06
    热爱
    -0.06
    quartered
    -0.06
    POSITIVE LOGITS
     adamant
    0.07
    祸
    0.07
    關於
    0.06
    豇
    0.06
    له
    0.06
    _Game
    0.06
     straw
    0.06
    عجز
    0.06
     Repeat
    0.06
     Chí
    0.06
    Act Density 0.086%

    No Known Activations