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

    Neuronpedia

    INDEX
    Explanations

    URLs or web links to images

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

    PyAY url

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.37
     birth
    -0.28
     http
    -0.28
    .
    -0.28
     https
    -0.27
    :
    -0.26
     {
    -0.26
     The
    -0.26
     $
    -0.26
     company
    -0.25
    POSITIVE LOGITS
     CanadaChoose
    0.84
    ロウィン
    0.83
    <unused14>
    0.83
    <unused41>
    0.82
    <unused74>
    0.82
    [@BOS@]
    0.82
    <unused43>
    0.82
    <unused52>
    0.82
    <unused8>
    0.82
    <unused16>
    0.82
    Act Density 0.029%

    No Known Activations