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

    Neuronpedia

    INDEX
    Explanations

    coding syntax involving variable assignments and definitions

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

    code punctuation and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -1.09
     Infórmanos
    -0.95
    AndEndTag
    -0.95
    WriteTagHelper
    -0.90
    httphttps
    -0.83
     HasFactory
    -0.82
    DockStyle
    -0.82
    styleType
    -0.80
    featureID
    -0.79
     Мексичка
    -0.79
    POSITIVE LOGITS
     and
    0.37
     Le
    0.34
     —
    0.34
    </b>
    0.33
     all
    0.32
     de
    0.32
     Team
    0.32
    Core
    0.32
     Core
    0.31
     a
    0.31
    Act Density 0.039%

    No Known Activations