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

    Neuronpedia

    INDEX
    Explanations

    second

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Archae
    -0.07
     director
    -0.06
     dors
    -0.06
    beginTransaction
    -0.06
    Communication
    -0.06
     Sebast
    -0.06
    鐵
    -0.06
     drawings
    -0.06
     Godzilla
    -0.06
    pués
    -0.06
    POSITIVE LOGITS
    pos
    0.07
     //"
    0.06
    succ
    0.06
    大家
    0.06
    iliyor
    0.06
    igned
    0.06
    راد
    0.06
    cbc
    0.06
    Products
    0.06
    INAL
    0.06
    Act Density 0.071%

    No Known Activations