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

    Neuronpedia

    INDEX
    Explanations

    content related to breaking news or updates

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

    start of a sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ロウィン
    -1.52
     queſta
    -1.50
    <unused16>
    -1.45
    <unused74>
    -1.45
    <unused41>
    -1.45
    [@BOS@]
    -1.45
    <unused52>
    -1.45
    <unused68>
    -1.45
    <unused43>
    -1.45
    <unused3>
    -1.45
    POSITIVE LOGITS
    The
    0.79
    In
    0.69
     
    0.69
    1
    0.65
    _
    0.63
    A
    0.63
    I
    0.63
    2
    0.59
    As
    0.58
    (
    0.58
    Act Density 0.010%

    No Known Activations