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

    Neuronpedia

    INDEX
    Explanations

    intentions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ỷ
    -0.08
    祈祷
    -0.07
    (ListNode
    -0.07
     luckily
    -0.07
    SetValue
    -0.07
     imprisoned
    -0.07
    Ленин
    -0.07
    ANDROID
    -0.07
     Goblin
    -0.07
    oblin
    -0.07
    POSITIVE LOGITS
    _EDGE
    0.07
    骧
    0.07
    -star
    0.07
    高的
    0.07
    名列
    0.07
     Muj
    0.07
     �
    0.07
     fmt
    0.07
     HS
    0.07
     least
    0.07
    Act Density 0.060%

    No Known Activations