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

    Neuronpedia

    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Logic
    -0.27
    logic
    -0.26
     ze
    -0.26
    _logic
    -0.26
    زر
    -0.25
     logic
    -0.25
    Logic
    -0.24
    velt
    -0.24
    /Gate
    -0.24
     AttributeSet
    -0.24
    POSITIVE LOGITS
    èĢ¸
    0.28
    (PC
    0.28
    =num
    0.26
     Gri
    0.25
    gary
    0.24
    åºł
    0.24
    禧
    0.24
    .li
    0.24
    è¿Ļ个æĹ¶ä»£
    0.23
    aware
    0.23
    Act Density 0.065%

    No Known Activations