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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    жди
    -0.07
     reproduce
    -0.07
     }↵↵↵
    -0.07
     ther
    -0.07
    .Node
    -0.07
    rage
    -0.07
    #!/
    -0.06
    ディ
    -0.06
     templ
    -0.06
    raph
    -0.06
    POSITIVE LOGITS
    (engine
    0.07
    万
    0.07
    attach
    0.06
    雙
    0.06
    ARG
    0.06
     올
    0.06
     comprised
    0.06
    Cisco
    0.06
    остей
    0.06
    ınızda
    0.06
    Act Density 0.011%

    No Known Activations