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

    Neuronpedia

    INDEX
    Explanations

    introductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ид
    -0.07
    لل
    -0.06
    structuring
    -0.06
    <Player
    -0.06
    Elements
    -0.06
    .bd
    -0.06
    ливо
    -0.06
    یف
    -0.06
    ोकर
    -0.06
    ่าว
    -0.06
    POSITIVE LOGITS
     Jess
    0.07
     parachute
    0.07
    405
    0.07
    ="/">
    0.07
     Mis
    0.06
     tái
    0.06
     confines
    0.06
     chemical
    0.06
     Bras
    0.06
     atomic
    0.06
    Act Density 0.001%

    No Known Activations