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

    Neuronpedia

    INDEX
    Explanations

    extra, additional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ajar
    -0.07
     и
    -0.06
    .Nodes
    -0.06
    aksi
    -0.06
    -arm
    -0.06
    -0.06
     verze
    -0.06
    .chat
    -0.06
     Sản
    -0.06
    pipe
    -0.06
    POSITIVE LOGITS
    Alive
    0.07
     extra
    0.07
     Wag
    0.06
    ्छ
    0.06
     Hubb
    0.06
    Win
    0.06
    Elements
    0.06
     ecs
    0.06
    衣
    0.06
    CH
    0.06
    Act Density 0.013%

    No Known Activations