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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HE
    -0.07
    	LOG
    -0.06
    웨
    -0.06
    抜
    -0.06
     whoever
    -0.06
    OMUX
    -0.06
    ekim
    -0.06
    _MEMBER
    -0.06
    ัสด
    -0.06
     کمتر
    -0.06
    POSITIVE LOGITS
     innov
    0.06
    寶
    0.06
    Hung
    0.06
     stren
    0.06
     federal
    0.06
     bicycles
    0.06
    "text
    0.06
    "↵↵↵
    0.06
     паци
    0.06
     Stan
    0.06
    Act Density 0.202%

    No Known Activations