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

    Neuronpedia

    INDEX
    Explanations

    text fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ellipt
    -0.07
    誰
    -0.06
     Scholars
    -0.06
     sitcom
    -0.06
     stal
    -0.06
     enrolled
    -0.06
     inward
    -0.06
     constr
    -0.06
     Governor
    -0.06
     campuses
    -0.06
    POSITIVE LOGITS
    /Delete
    0.07
     Atomic
    0.07
     متوسط
    0.07
     đình
    0.07
     sx
    0.06
    ƒ
    0.06
     dapat
    0.06
    edish
    0.06
     Hep
    0.06
    えて
    0.06
    Act Density 0.000%

    No Known Activations