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
     follando
    -0.07
    Distribution
    -0.06
    Titan
    -0.06
     Toys
    -0.06
    aremos
    -0.06
     mů
    -0.06
    egl
    -0.06
    warehouse
    -0.06
     нею
    -0.06
     Essentials
    -0.06
    POSITIVE LOGITS
     Biggest
    0.06
    FEATURE
    0.06
     pointer
    0.06
     Kı
    0.06
     poison
    0.06
     disrupting
    0.06
     breakout
    0.06
     treason
    0.06
     Đề
    0.06
    emie
    0.06
    Act Density 0.258%

    No Known Activations