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

    Neuronpedia

    INDEX
    Explanations

    references to programming functions and their structures

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

    PHP code or data structures

    np_acts-logits-general · gemini-2.0-flash

    request string parameter access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.76
     ujednoznacz
    -0.62
    aterally
    -0.61
    ingabe
    -0.59
     initComponents
    -0.59
    beled
    -0.57
    :+:
    -0.56
    )':
    -0.56
     זו
    -0.55
    ]){
    -0.55
    POSITIVE LOGITS
     himſelf
    0.54
     Smarty
    0.51
    SuppressLint
    0.49
    Diweddarwch
    0.49
    writeFieldEnd
    0.49
     pleaſure
    0.49
     themſelves
    0.48
    sprechend
    0.48
     houſe
    0.47
     purpoſe
    0.46
    Act Density 0.110%

    No Known Activations