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

    Neuronpedia

    INDEX
    Explanations

    reported

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dinosaur
    -0.07
    ภายใน
    -0.07
    _gps
    -0.06
     například
    -0.06
    Av
    -0.06
    ERGE
    -0.06
    टन
    -0.06
     Psi
    -0.06
     Πανεπ
    -0.06
     renov
    -0.06
    POSITIVE LOGITS
    誌
    0.07
    ưỡng
    0.07
    _lineno
    0.07
     newcom
    0.06
    ğmen
    0.06
     terrorists
    0.06
    挑
    0.06
     parms
    0.06
    _One
    0.06
    .ManyToMany
    0.06
    Act Density 0.016%

    No Known Activations