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

    Neuronpedia

    INDEX
    Explanations

    punctuation usage, particularly commas, in varying contexts

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

    greets, here, there, you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poveznice
    -0.40
    windowFixed
    -0.35
    BarStyle
    -0.34
     banget
    -0.34
     TAMBÉM
    -0.34
     leksikon
    -0.33
     Thank
    -0.32
    jr
    -0.32
     Италијани
    -0.32
    קישורים
    -0.31
    POSITIVE LOGITS
    Tikang
    0.60
     BoxFit
    0.55
     socialize
    0.52
     manipulate
    0.50
     suffer
    0.50
    twimg
    0.49
     interact
    0.49
    clerView
    0.49
     mobilize
    0.48
    ponses
    0.48
    Act Density 0.128%

    No Known Activations