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

    Neuronpedia

    INDEX
    Explanations

    comput

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     faith
    -0.07
    لو
    -0.06
     loving
    -0.06
     Canton
    -0.06
    Subject
    -0.06
     workshops
    -0.06
     read
    -0.06
    loit
    -0.06
     samp
    -0.06
    ourt
    -0.06
    POSITIVE LOGITS
     (("
    0.07
     goal
    0.07
    NPC
    0.06
    +"_
    0.06
    μαι
    0.06
    _SS
    0.06
    Meal
    0.06
    "text
    0.06
     bez
    0.06
    _DE
    0.06
    Act Density 0.015%

    No Known Activations