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

    Neuronpedia

    INDEX
    Explanations

    instances of function call expectations and their associated return values or results

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

    `false` boolean checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -1.06
    Personendaten
    -0.95
     queſta
    -0.94
     Normdatei
    -0.86
    batore
    -0.84
     ſind
    -0.79
    AndEndTag
    -0.79
     $_(
    -0.79
     invokingState
    -0.79
    enderror
    -0.75
    POSITIVE LOGITS
     ==
    0.29
     expectations
    0.28
    ==
    0.28
     brisa
    0.28
     =
    0.26
     !=
    0.23
     amélior
    0.23
     ===
    0.23
     sharp
    0.23
     felicidad
    0.23
    Act Density 0.012%

    No Known Activations