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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flats
    -0.07
    .New
    -0.07
     кого
    -0.07
     colder
    -0.06
    世界
    -0.06
    dae
    -0.06
     thresh
    -0.06
     SWT
    -0.06
    _zoom
    -0.06
     loads
    -0.06
    POSITIVE LOGITS
    [selected
    0.07
     dream
    0.06
    _PLAN
    0.06
    leground
    0.06
    Ngh
    0.06
    ließlich
    0.06
    ========
    0.06
    腾
    0.06
    ---------
    0.06
     tq
    0.06
    Act Density 0.047%

    No Known Activations