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

    Neuronpedia

    INDEX
    Explanations

    symbols or characters used for greater-than comparisons

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

    Text after ">" or before math symbols

    np_acts-logits-general · gemini-2.0-flash

    greater than symbol or quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    son
    -0.59
    ation
    -0.57
    istic
    -0.53
    '
    -0.53
    (
    -0.52
    лю
    -0.48
    ate
    -0.48
     the
    -0.47
     Lo
    -0.46
    XtraGrid
    -0.45
    POSITIVE LOGITS
    >>>>>>>>
    1.31
    >>>>>>>
    1.23
    >>>>
    1.22
    >>>>>>
    1.22
    >>>
    1.11
    displayquote
    1.10
    .>
    1.10
    }>\
    1.07
    _<
    1.05
    _>
    1.05
    Act Density 0.255%

    No Known Activations