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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Keeps
    -0.06
     meme
    -0.06
    ्षक
    -0.06
     decl
    -0.06
     Nikola
    -0.06
    ocol
    -0.06
    _BOOT
    -0.06
    ?v
    -0.06
    elder
    -0.06
    razier
    -0.06
    POSITIVE LOGITS
    具
    0.07
     ((!
    0.07
     درس
    0.07
     Wichita
    0.07
     ใช
    0.07
    _not
    0.06
    られ
    0.06
    稍
    0.06
    ään
    0.06
    date
    0.06
    Act Density 0.007%

    No Known Activations