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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ว
    -0.07
    ща
    -0.07
    _playing
    -0.07
     αυτά
    -0.06
     '+'
    -0.06
    Widgets
    -0.06
    ibraries
    -0.06
    /topic
    -0.06
    야
    -0.06
     yaparak
    -0.06
    POSITIVE LOGITS
     discretionary
    0.06
     ліка
    0.06
    .Cell
    0.06
     خان
    0.06
    個
    0.06
    Projects
    0.06
    auto
    0.06
    Short
    0.06
    атель
    0.06
     undermined
    0.06
    Act Density 0.024%

    No Known Activations