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

    Neuronpedia

    INDEX
    Explanations

    personal experience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ırlar
    -0.08
     lick
    -0.07
     Kia
    -0.07
    环
    -0.06
    bilt
    -0.06
     Rate
    -0.06
    esian
    -0.06
     agar
    -0.06
    uştur
    -0.06
     dir
    -0.06
    POSITIVE LOGITS
     uyg
    0.08
    enegro
    0.07
    .getContent
    0.07
    ille
    0.06
    �
    0.06
     aday
    0.06
     spécial
    0.06
     several
    0.06
    idata
    0.06
    .Secret
    0.06
    Act Density 0.149%

    No Known Activations