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

    Neuronpedia

    INDEX
    Explanations

    academic/scientific abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sim
    -0.08
    育
    -0.07
    八大
    -0.07
    .est
    -0.07
     Ash
    -0.07
     =↵↵
    -0.06
     ramps
    -0.06
    Alternatively
    -0.06
    umb
    -0.06
     silica
    -0.06
    POSITIVE LOGITS
    �
    0.08
    liche
    0.07
     pública
    0.07
    ]),
    0.07
     ###
    0.06
    字样
    0.06
     aberr
    0.06
    stellen
    0.06
    >--}}↵
    0.06
    escort
    0.06
    Act Density 0.002%

    No Known Activations