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

    Neuronpedia

    INDEX
    Explanations

    code/comments/signatures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     localtime
    -0.07
     Flame
    -0.06
    里
    -0.06
    Sa
    -0.06
     Square
    -0.06
     statutory
    -0.06
     пацієн
    -0.06
    lx
    -0.06
    鑑
    -0.06
     میشود
    -0.06
    POSITIVE LOGITS
    orient
    0.07
    arcer
    0.06
    ickle
    0.06
    @g
    0.06
    udget
    0.06
     osg
    0.06
     strán
    0.06
    behavior
    0.06
    alloc
    0.06
    浴
    0.06
    Act Density 0.251%

    No Known Activations