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

    Neuronpedia

    INDEX
    Explanations

    snippets or references in structured documents

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

    ctypes Function parameter greater

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.56
    InjectAttribute
    -0.55
    Vidite
    -0.50
    #+#
    -0.46
    PreferredItem
    -0.46
    MLLoader
    -0.46
    tonode
    -0.45
    __(/*!
    -0.44
     חיצוניים
    -0.43
    zbęd
    -0.42
    POSITIVE LOGITS
    ᕗ
    0.44
    0.43
    UnusedPrivate
    0.43
    TagMode
    0.41
    Véxase
    0.40
    возь
    0.38
     Tratt
    0.37
    spli
    0.37
    umbered
    0.36
     Bier
    0.36
    Act Density 0.119%

    No Known Activations