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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "look" or expressions that prompt visual attention or observation

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

    look at this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tableFuture
    -0.50
     raczej
    -0.42
     jälkeen
    -0.42
     particulières
    -0.40
    EOD
    -0.40
    UserScript
    -0.39
     endblock
    -0.39
    LayoutStyle
    -0.38
     pihaknya
    -0.38
    stylers
    -0.37
    POSITIVE LOGITS
    GIVEREF
    0.63
     المعيارى
    0.58
    NullCheck
    0.57
    Look
    0.56
    ardez
    0.55
     Behold
    0.53
    Behold
    0.52
    点此举报
    0.50
    Observe
    0.50
    Normalize
    0.49
    Act Density 0.019%

    No Known Activations