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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    رسی
    -0.06
    .StartsWith
    -0.06
    رفته
    -0.06
     α
    -0.06
     danced
    -0.06
    orget
    -0.06
    หมด
    -0.06
    Solid
    -0.06
     высокой
    -0.06
     dik
    -0.06
    POSITIVE LOGITS
     düşünc
    0.07
     glide
    0.07
     tai
    0.07
    ATOM
    0.07
    how
    0.07
    218
    0.07
     ActionResult
    0.06
     bushes
    0.06
     especially
    0.06
     UIF
    0.06
    Act Density 0.001%

    No Known Activations