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

    Neuronpedia

    INDEX
    Explanations

    really

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lagos
    -0.06
     commenting
    -0.06
     foo
    -0.06
    $user
    -0.06
    /goto
    -0.06
     schemes
    -0.06
    rah
    -0.06
    _pci
    -0.06
     Fah
    -0.06
    rend
    -0.06
    POSITIVE LOGITS
    东西
    0.06
     وف
    0.06
     représ
    0.06
     нич
    0.06
     �
    0.06
    аться
    0.06
    ODY
    0.06
     आश
    0.06
     сказал
    0.06
     佛
    0.06
    Act Density 0.426%

    No Known Activations