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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Goat
    -0.07
     Georges
    -0.07
     başına
    -0.06
    /****************************************************************
    -0.06
     ServiceProvider
    -0.06
    도의
    -0.06
    ότητα
    -0.06
     pož
    -0.06
    Seeder
    -0.06
    pseudo
    -0.06
    POSITIVE LOGITS
     prevailed
    0.07
     how
    0.06
     aggreg
    0.06
     qualitative
    0.06
     ECC
    0.06
    kin
    0.06
     hay
    0.06
    UPPORT
    0.06
    _large
    0.06
    kal
    0.06
    Act Density 0.004%

    No Known Activations