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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    celand
    -0.07
     décor
    -0.06
    avar
    -0.06
     Innovation
    -0.06
    .AI
    -0.06
    ensors
    -0.06
     Pays
    -0.06
     Sensors
    -0.06
     BALL
    -0.06
     Labs
    -0.06
    POSITIVE LOGITS
    งค
    0.06
    �
    0.06
    基本
    0.06
     попыт
    0.06
    行動
    0.06
     سطح
    0.06
    ją
    0.06
     Tôi
    0.06
     растений
    0.06
    typeid
    0.06
    Act Density 0.906%

    No Known Activations