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

    Neuronpedia

    INDEX
    Explanations

    various types of textual elements and structural components in written documents

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

    during each

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.63
    UnusedPrivate
    -0.54
    -0.52
    RTEE
    -0.51
    swire
    -0.51
    ISupport
    -0.51
    findpost
    -0.50
    -0.49
    BeginInit
    -0.48
    $_['
    -0.47
    POSITIVE LOGITS
    település
    0.44
     Савез
    0.39
    TacToe
    0.38
    zubauen
    0.38
    省市镇
    0.36
    는데
    0.35
     MainAxisSize
    0.35
    pagest
    0.35
    CPM
    0.34
    falgar
    0.33
    Act Density 0.382%

    No Known Activations