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

    Neuronpedia

    INDEX
    Explanations

    elements and attributes related to preferences and settings in a structured format

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

    preference keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plá
    -0.34
     bás
    -0.31
    DockStyle
    -0.29
     trạng
    -0.29
    ffindor
    -0.28
    초
    -0.27
    ErrUnexpectedEOF
    -0.27
    Filmographie
    -0.27
    듯
    -0.27
     bandou
    -0.26
    POSITIVE LOGITS
     nahilalakip
    0.65
     preference
    0.62
    Preference
    0.61
    preference
    0.58
    OGND
    0.57
     Preference
    0.56
    Tikang
    0.54
    ❉
    0.54
     Administrativna
    0.54
     ligiloj
    0.53
    Act Density 0.012%

    No Known Activations