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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and various instances of 'the'

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

    numbers, references, and specific details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bezeichneter
    -0.45
    tinyos
    -0.44
    WSGI
    -0.40
    expandindo
    -0.38
    tangentMode
    -0.37
     Mild
    -0.37
    setVerticalGroup
    -0.37
     Hints
    -0.35
    Démographie
    -0.35
     Did
    -0.35
    POSITIVE LOGITS
    ]")]
    0.50
    期刊论文
    0.45
     مرئيه
    0.45
     nargin
    0.44
    ViewFeatures
    0.44
     tartalomajánló
    0.43
    arrings
    0.42
    fions
    0.42
    LookAnd
    0.42
     prijzen
    0.42
    Act Density 0.148%

    No Known Activations