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

    Neuronpedia

    INDEX
    Explanations

    literature and nature descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ındaki
    -0.08
     Berufs
    -0.08
    Раб
    -0.08
     ZA
    -0.08
    ZE
    -0.08
     severely
    -0.07
    "in
    -0.07
     режим
    -0.07
     Arbeit
    -0.07
    zilla
    -0.07
    POSITIVE LOGITS
    树林
    0.10
     perch
    0.09
     sin
    0.09
     gums
    0.08
     lotus
    0.08
     blooms
    0.08
     gemstone
    0.08
     flowers
    0.08
     sweater
    0.08
     Eiffel
    0.08
    Act Density 0.069%

    No Known Activations