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

    Neuronpedia

    INDEX
    Explanations

    Question mark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resemblance
    -0.07
    没啥
    -0.07
     eldest
    -0.07
    תקבל
    -0.07
    一声
    -0.07
    深化改革
    -0.06
     muff
    -0.06
    を持
    -0.06
     remarked
    -0.06
     אמנ
    -0.06
    POSITIVE LOGITS
    ODB
    0.07
    setFont
    0.07
     Corpus
    0.07
    LAB
    0.07
     wordpress
    0.07
    _params
    0.07
    _modified
    0.07
    Into
    0.07
    🍝
    0.07
    	DBG
    0.07
    Act Density 0.234%

    No Known Activations