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

    Neuronpedia

    INDEX
    Explanations

    root

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     meg
    -0.07
     yetiş
    -0.07
     переход
    -0.07
     десят
    -0.06
     입력
    -0.06
    _the
    -0.06
     новых
    -0.06
     feats
    -0.06
    elm
    -0.06
     hot
    -0.06
    POSITIVE LOGITS
    ffiti
    0.07
    ');?></
    0.06
    rı
    0.06
    ng
    0.06
     Hill
    0.06
     weap
    0.06
     rw
    0.06
    NotBlank
    0.06
     začal
    0.06
     Rox
    0.06
    Act Density 0.003%

    No Known Activations