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

    Neuronpedia

    INDEX
    Explanations

    choosing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ISBN
    -0.07
     Wikipedia
    -0.07
    washing
    -0.06
    .Uri
    -0.06
    vider
    -0.06
    Adjusted
    -0.06
     Valentine
    -0.06
    ViewState
    -0.06
    嗎
    -0.06
     onPause
    -0.06
    POSITIVE LOGITS
     現
    0.06
    анов
    0.06
     регулю
    0.06
    _FIND
    0.06
    _prim
    0.06
     procure
    0.06
    ................
    0.06
    .styles
    0.06
    官方
    0.06
     ブ
    0.06
    Act Density 0.064%

    No Known Activations