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

    Neuronpedia

    INDEX
    Explanations

    numerical representations and values

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

    timestamps with colons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RTSN
    -0.54
     Roskov
    -0.50
     otomatig
    -0.49
    참고
    -0.45
    ########.
    -0.44
     noDo
    -0.44
     useAuth
    -0.44
    ronpa
    -0.44
    Viited
    -0.43
    UObject
    -0.43
    POSITIVE LOGITS
     Bioaccumulative
    0.48
     CreateTagHelper
    0.42
     przec
    0.41
     boneca
    0.40
     sürü
    0.39
     vernünf
    0.39
     législ
    0.38
     aydın
    0.37
    zeß
    0.37
     idéia
    0.37
    Act Density 0.071%

    No Known Activations