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

    Neuronpedia

    INDEX
    Explanations

    references to academic composition and writing processes

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

    written content or products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Catawiki
    -0.48
     Normdatei
    -0.44
    sproz
    -0.39
    inander
    -0.37
     Dependent
    -0.36
    向
    -0.36
    立
    -0.35
    得
    -0.34
     Balancing
    -0.34
    equalTo
    -0.33
    POSITIVE LOGITS
    0.62
    ::_('
    0.58
    Diweddarwch
    0.56
    isNameExpr
    0.56
    felves
    0.55
    Hochspringen
    0.54
    \{\\
    0.54
     $_"
    0.52
    .*")]
    0.51
     ſind
    0.51
    Act Density 0.046%

    No Known Activations