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

    Neuronpedia

    INDEX
    Explanations

    HTML tags or XML-like structures

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

    after a name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.95
    IContainer
    -0.90
    ⟬
    -0.85
     AppCompatTheme
    -0.84
    нгред
    -0.83
     fashiola
    -0.79
    ロウィン
    -0.79
     '\\;'
    -0.79
    ſicht
    -0.78
    NamedQueries
    -0.78
    POSITIVE LOGITS
    1
    0.44
    ↵
    0.42
    </blockquote>
    0.39
    The
    0.39
    2
    0.38
    Yes
    0.36
    ↵↵
    0.35
    I
    0.35
    After
    0.34
    By
    0.33
    Act Density 0.002%

    No Known Activations