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

    Neuronpedia

    INDEX
    Explanations

    makeup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    platform
    -0.08
     neighborhoods
    -0.07
     haci
    -0.07
     Selling
    -0.07
     permutation
    -0.07
    _UI
    -0.07
    ്�
    -0.06
     gal
    -0.06
     Insight
    -0.06
     struggles
    -0.06
    POSITIVE LOGITS
    ellular
    0.07
    .POS
    0.07
     oslo
    0.07
    mişti
    0.06
     افراد
    0.06
    เทศ
    0.06
    iteleri
    0.06
    atoire
    0.06
    >");↵↵
    0.06
     nao
    0.06
    Act Density 0.017%

    No Known Activations