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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and personal sentiment

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

    codes and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.46
     descubrimiento
    -0.45
     informaciones
    -0.43
     recomendaciones
    -0.42
    Và
    -0.42
     Савезне
    -0.42
    PointerException
    -0.41
     officiels
    -0.40
    stdc
    -0.40
     Erkennt
    -0.38
    POSITIVE LOGITS
    httphttps
    0.63
    matchCondition
    0.52
    ✨:
    0.49
     initComponents
    0.47
    
    0.44
    ulets
    0.43
    phous
    0.43
     createState
    0.43
    XO
    0.43
     red
    0.41
    Act Density 0.035%

    No Known Activations