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

    Neuronpedia

    INDEX
    Explanations

    Leap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    usr
    -0.07
     کاملا
    -0.07
    Sections
    -0.07
     Apartment
    -0.06
     Copper
    -0.06
     checkboxes
    -0.06
     SEL
    -0.06
    [id
    -0.06
     Apple
    -0.06
    51
    -0.06
    POSITIVE LOGITS
    :M
    0.08
     Insight
    0.07
    الم
    0.07
     đảo
    0.07
    actus
    0.07
    attack
    0.06
    ‰
    0.06
     成
    0.06
    kü
    0.06
    तम
    0.06
    Act Density 0.118%

    No Known Activations