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

    Neuronpedia

    INDEX
    Explanations

    counting characters in paragraphs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _resources
    -0.09
    Renew
    -0.09
    quired
    -0.08
     перевоз
    -0.08
    _cache
    -0.08
     വിദ്യാഭ്യാസ
    -0.08
    _confirm
    -0.08
    renew
    -0.08
    _apps
    -0.08
     Mitchell
    -0.08
    POSITIVE LOGITS
    平均
    0.09
    يم
    0.09
     uneven
    0.09
     paragraphs
    0.08
    均
    0.08
    .mean
    0.08
     evenly
    0.08
    .lines
    0.08
     paragraph
    0.08
    IIII
    0.08
    Act Density 0.016%

    No Known Activations