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

    Neuronpedia

    INDEX
    Explanations

    programming language syntax and structure elements

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

    import, class, user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -1.01
    <unused41>
    -0.96
    [@BOS@]
    -0.96
    <unused28>
    -0.96
    <unused17>
    -0.96
    <unused8>
    -0.96
    <unused43>
    -0.96
    <unused74>
    -0.96
    <pad>
    -0.95
    <unused3>
    -0.95
    POSITIVE LOGITS
    1
    0.31
     place
    0.30
     sp
    0.29
     guy
    0.28
     
    0.27
     all
    0.26
     k
    0.26
    .
    0.25
     Stunde
    0.25
     πά
    0.24
    Act Density 0.014%

    No Known Activations