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

    Neuronpedia

    INDEX
    Explanations

    actions and processes related to instruction and control

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    effecting, instructing, reducing, applying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infór
    -0.63
    Jeografia
    -0.60
     propOrder
    -0.58
    FormTagHelper
    -0.57
     dezelve
    -0.51
     ainfi
    -0.50
     desmotivaciones
    -0.49
    iſter
    -0.48
     المعيارى
    -0.48
     Geſch
    -0.47
    POSITIVE LOGITS
     via
    0.55
    __":
    0.48
    HtmlAttribute
    0.47
    via
    0.43
     through
    0.42
     mediante
    0.42
    __":
    0.38
    MethodManager
    0.37
    __':
    0.36
     шля
    0.35
    Act Density 0.993%

    No Known Activations