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

    Neuronpedia

    INDEX
    Explanations

    academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     içeren
    -0.07
    ifs
    -0.07
    妃
    -0.06
    \xd
    -0.06
    ляться
    -0.06
    aph
    -0.06
     hast
    -0.06
    ης
    -0.06
    Disable
    -0.06
     Với
    -0.06
    POSITIVE LOGITS
     sniper
    0.06
     breakup
    0.06
     "${
    0.06
     Broncos
    0.06
     머
    0.06
    allele
    0.06
     Adolf
    0.06
     σκ
    0.06
    Compiled
    0.06
     LIB
    0.06
    Act Density 0.094%

    No Known Activations