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

    Neuronpedia

    INDEX
    Explanations

    measurability and definition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intend
    -0.07
    هور
    -0.06
    osu
    -0.06
    Profile
    -0.06
    _et
    -0.06
     Drum
    -0.06
     Furn
    -0.06
    !=
    -0.06
     soften
    -0.06
    .answer
    -0.06
    POSITIVE LOGITS
    .Exists
    0.07
    .sam
    0.07
     равно
    0.07
    olithic
    0.07
     Lager
    0.06
    liğini
    0.06
    柏
    0.06
    sdale
    0.06
    ensibly
    0.06
     Sy
    0.06
    Act Density 0.033%

    No Known Activations