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

    Neuronpedia

    INDEX
    Explanations

    correcting misinformation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .glob
    -0.07
    ças
    -0.07
    ột
    -0.06
    failed
    -0.06
     topl
    -0.06
    Χ
    -0.06
     alır
    -0.06
    ByUsername
    -0.06
    BOTTOM
    -0.06
     Symphony
    -0.06
    POSITIVE LOGITS
    vac
    0.07
     geld
    0.06
    darwin
    0.06
    اجات
    0.06
    ่างก
    0.06
     clang
    0.06
     mnemonic
    0.06
    arget
    0.06
    経
    0.06
    비아
    0.06
    Act Density 0.044%

    No Known Activations