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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts, particularly related to functions and variable management in code

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

    starting words or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.67
     שוליים
    -0.64
     invokingState
    -0.58
     nakalista
    -0.57
    脚注の使い方
    -0.57
     تكبرها
    -0.56
     []:
    -0.54
     الحره
    -0.54
    Clik
    -0.53
    Архівовано
    -0.53
    POSITIVE LOGITS
     betweenstory
    0.38
     scolas
    0.35
     Abweich
    0.34
     conoscenza
    0.32
    áus
    0.32
     spesa
    0.32
    uestamente
    0.32
    Ikus
    0.32
     dizaines
    0.32
    ukkah
    0.31
    Act Density 0.985%

    No Known Activations