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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     talks
    -0.07
     beds
    -0.07
    �认
    -0.07
    ーカー
    -0.07
    Radi
    -0.07
    ediği
    -0.07
     radi
    -0.07
    Toyota
    -0.07
     convey
    -0.06
     echoes
    -0.06
    POSITIVE LOGITS
    /contact
    0.07
     مادر
    0.06
     Rede
    0.06
     Advice
    0.06
    なた
    0.06
    goal
    0.06
     qos
    0.05
    Khi
    0.05
     walker
    0.05
    RunWith
    0.05
    Act Density 0.080%

    No Known Activations