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

    Neuronpedia

    INDEX
    Explanations

    TODO comments or annotations in code

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

    "TODO" or similar task-related terms

    np_acts-logits-general · gemini-2.0-flash

    TODO comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.67
     &___
    -0.59
    oredCriteria
    -0.56
     ddelweddau
    -0.54
     berke
    -0.51
    FilterChain
    -0.51
     Erscheinung
    -0.50
    Suomen
    -0.47
    Pautan
    -0.47
    readFileSync
    -0.47
    POSITIVE LOGITS
    TODO
    0.97
     TODO
    0.94
    todo
    0.71
    Todo
    0.68
     Infórmanos
    0.68
    domada
    0.67
     NOTE
    0.66
    InputModule
    0.66
    PDATE
    0.63
     noDo
    0.63
    Act Density 0.015%

    No Known Activations