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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FINISH
    -0.07
    �
    -0.07
    PROP
    -0.06
    /Open
    -0.06
     THR
    -0.06
    ीव
    -0.06
    選択
    -0.06
    zew
    -0.06
     ngôi
    -0.06
     Oper
    -0.06
    POSITIVE LOGITS
     مشخص
    0.06
    hud
    0.06
    _tab
    0.06
    _done
    0.06
    出し
    0.06
     itself
    0.06
     Efficiency
    0.06
    _am
    0.06
     denying
    0.06
     этой
    0.06
    Act Density 0.040%

    No Known Activations