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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zákon
    -0.07
    %↵
    -0.07
     خورد
    -0.07
     sondern
    -0.07
    Ð
    -0.07
    数组
    -0.06
    _TOP
    -0.06
    _ELEMENT
    -0.06
     pueden
    -0.06
    Framebuffer
    -0.06
    POSITIVE LOGITS
     /.
    0.07
     stole
    0.06
    PECIAL
    0.06
     Unsafe
    0.06
     opposes
    0.06
     //~
    0.06
     improvis
    0.06
    ويت
    0.06
    Mul
    0.06
     な
    0.06
    Act Density 0.078%

    No Known Activations