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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to policies and regulations, particularly in educational and legal contexts

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

    bans and restrictive policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.58
    AndEndTag
    -0.48
    xymatrix
    -0.47
    ⤹
    -0.46
     '\\;'
    -0.46
    httphttps
    -0.45
    canestro
    -0.44
     AssemblyCulture
    -0.43
     OMITBAD
    -0.41
     fleuve
    -0.41
    POSITIVE LOGITS
     discriminate
    0.40
    CopyWith
    0.39
     Harassment
    0.38
     bans
    0.38
    ScreenState
    0.38
    /**
    0.38
    quette
    0.37
    󠁣
    0.37
    Escola
    0.37
    felves
    0.37
    Act Density 0.028%

    No Known Activations