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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ба
    -0.06
     bubb
    -0.06
    ุป
    -0.06
     whisper
    -0.06
     flick
    -0.06
     gran
    -0.06
    ители
    -0.06
    YP
    -0.06
    Positive
    -0.06
    ために
    -0.06
    POSITIVE LOGITS
    ·
    0.07
     websocket
    0.07
    449
    0.06
     """.
    0.06
    ]*(
    0.06
     ابتدا
    0.06
    yclerview
    0.06
     hoses
    0.06
     Boise
    0.06
     ugl
    0.06
    Act Density 0.004%

    No Known Activations