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

    Neuronpedia

    INDEX
    Explanations

    solutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _topic
    -0.06
    她
    -0.06
     digits
    -0.06
    áře
    -0.06
    .Ver
    -0.06
    rv
    -0.06
    rnd
    -0.06
     rè
    -0.06
     merely
    -0.06
     porque
    -0.06
    POSITIVE LOGITS
    ΥΣ
    0.07
     Korea
    0.07
     Social
    0.07
     −
    0.07
     comeback
    0.07
     Especially
    0.07
     interacts
    0.06
     simultaneously
    0.06
    لعاب
    0.06
    lius
    0.06
    Act Density 0.003%

    No Known Activations