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

    Neuronpedia

    INDEX
    Explanations

    awards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inadvert
    -0.07
    (rec
    -0.07
    Success
    -0.07
     crushed
    -0.07
    exp
    -0.06
    ango
    -0.06
     mais
    -0.06
    mates
    -0.06
    IRON
    -0.06
    ison
    -0.06
    POSITIVE LOGITS
    กำ
    0.08
    882
    0.07
     극
    0.06
    ายใน
    0.06
     ########.
    0.06
    .Many
    0.06
    діл
    0.06
     brutality
    0.06
     skutečně
    0.06
     mutableListOf
    0.06
    Act Density 0.035%

    No Known Activations