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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to data structure or class definitions

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

    programming language keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    -0.34
     
    -0.32
    <strong>
    -0.28
     (
    -0.28
     “
    -0.26
    <i>
    -0.26
       
    -0.26
     lan
    -0.25
    be
    -0.25
     car
    -0.25
    POSITIVE LOGITS
    parsedMessage
    1.07
    OGND
    1.00
    Rhestr
    1.00
    GEBURTSDATUM
    1.00
     estekak
    0.97
     autorytatywna
    0.94
    <unused16>
    0.93
    Autoritní
    0.93
    <pad>
    0.92
    [@BOS@]
    0.92
    Act Density 0.021%

    No Known Activations