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

    Neuronpedia

    INDEX
    Explanations

    Uniqueness or singularity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amplify
    -0.08
     ellipt
    -0.08
    bera
    -0.08
    jay
    -0.08
     усил
    -0.07
    -0.07
    JAN
    -0.07
     dedicado
    -0.07
     ফেল
    -0.07
     ampl
    -0.07
    POSITIVE LOGITS
    版本
    0.13
     variante
    0.12
     Variante
    0.11
     vaihtoe
    0.11
    preferred
    0.10
     вариант
    0.10
     Variant
    0.10
    方案
    0.10
     вариан
    0.10
     संस्करण
    0.10
    Act Density 0.133%
    No Known Activations