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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EndProject
    -0.63
    fjspx
    -0.60
     umane
    -0.56
    ours
    -0.55
    Ours
    -0.55
    UVWXYZ
    -0.54
     progrès
    -0.54
    ulosa
    -0.53
     jadx
    -0.53
    thul
    -0.52
    POSITIVE LOGITS
    bability
    0.52
     any
    0.50
    نجليز
    0.49
     your
    0.48
     every
    0.48
    Xna
    0.47
    ælde
    0.45
     przyzna
    0.45
    ExecuteNonQuery
    0.43
     Ayuda
    0.43
    Act Density 0.003%

    No Known Activations