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

    Neuronpedia

    INDEX
    Explanations

    programming language constructs, particularly import statements and class definitions

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

    manager instance retrieval

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    beginPath
    -0.31
     bientôt
    -0.30
     bite
    -0.30
     tempt
    -0.30
    onta
    -0.30
     стороне
    -0.29
     deepen
    -0.29
    forEach
    -0.28
     blitz
    -0.28
     split
    -0.27
    POSITIVE LOGITS
     manager
    1.20
     Manager
    1.20
     MANAGER
    1.14
     managers
    1.14
    manager
    1.13
     Managers
    1.12
    managers
    1.12
    Manager
    1.11
    MANAGER
    1.06
    getManager
    0.99
    Act Density 0.011%

    No Known Activations