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

    Neuronpedia

    INDEX
    Explanations

    words related to authority and guidance in various contexts

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

    programming terms and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.55
     autorytatywna
    -0.40
     peggio
    -0.37
    Географиясе
    -0.36
    zelve
    -0.35
    Vegeu
    -0.35
     bestemt
    -0.34
     Мексичка
    -0.33
     incluidos
    -0.33
    ModelSerializer
    -0.33
    POSITIVE LOGITS
    AccessorTable
    0.51
     sonde
    0.50
    WriteAttribute
    0.50
    .*")]
    0.49
    ="@+
    0.48
     Initialized
    0.45
    setObjectName
    0.43
     препратки
    0.43
     typing
    0.43
     パンチラ
    0.43
    Act Density 0.045%

    No Known Activations