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

    Neuronpedia

    INDEX
    Explanations

    elements related to digital communication or technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    future predictions and urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transfieras
    -0.98
    ⟬
    -0.80
    Vidite
    -0.77
     оригіналу
    -0.76
    <unused52>
    -0.75
    <pad>
    -0.75
    OGND
    -0.75
    ########.
    -0.75
    [@BOS@]
    -0.75
    <unused8>
    -0.75
    POSITIVE LOGITS
    ↵↵
    0.36
     simple
    0.35
    <strong>
    0.34
    C
    0.34
    2
    0.33
    simple
    0.33
    3
    0.32
    Đ
    0.31
    <i>
    0.31
    from
    0.31
    Act Density 0.054%

    No Known Activations