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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wik
    -0.07
    اة
    -0.07
     програ
    -0.06
     konnte
    -0.06
     рост
    -0.06
    .KeyPress
    -0.06
     подроб
    -0.06
     đổ
    -0.06
    خدم
    -0.06
     nale
    -0.06
    POSITIVE LOGITS
    054
    0.07
    SN
    0.07
     Austria
    0.07
     Shah
    0.06
    past
    0.06
    dance
    0.06
    .Server
    0.06
    |null
    0.06
    ResourceId
    0.06
    sın
    0.06
    Act Density 0.035%

    No Known Activations