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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ben
    -0.06
     chall
    -0.06
    _GROUP
    -0.06
    ارهای
    -0.06
     Plex
    -0.06
    apsible
    -0.06
    emporary
    -0.06
     Gee
    -0.06
     postseason
    -0.06
     situated
    -0.06
    POSITIVE LOGITS
    �
    0.07
     bowling
    0.07
    Ос
    0.06
    vec
    0.06
    olar
    0.06
     choking
    0.06
    .bat
    0.06
    APSHOT
    0.06
     –↵↵
    0.06
    authority
    0.06
    Act Density 0.033%

    No Known Activations