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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adaptor
    -0.08
     Latino
    -0.07
     χρήση
    -0.07
     grille
    -0.07
     NSA
    -0.07
    ön
    -0.06
     mmc
    -0.06
    ряду
    -0.06
    ель
    -0.06
    another
    -0.06
    POSITIVE LOGITS
    _DOWN
    0.06
    .lr
    0.06
    ...",
    0.06
     teamwork
    0.06
    _PLAY
    0.06
    mouseleave
    0.06
     �
    0.06
    ++]=
    0.06
     ид
    0.06
    DWORD
    0.06
    Act Density 0.011%

    No Known Activations