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

    Neuronpedia

    INDEX
    Explanations

    reaction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     propos
    -0.08
     Twitter
    -0.07
     지도
    -0.06
    (IT
    -0.06
    Twitter
    -0.06
     cic
    -0.06
     giáo
    -0.06
    .spatial
    -0.06
    DEN
    -0.06
    ISTIC
    -0.06
    POSITIVE LOGITS
    ozí
    0.06
    0.06
     الول
    0.06
    sequence
    0.06
     Xuân
    0.06
    また
    0.06
    زینه
    0.06
    ======↵
    0.06
     native
    0.06
    หลวง
    0.06
    Act Density 0.016%

    No Known Activations