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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal identity and self-reflection

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

    First-person pronouns and related words

    np_acts-logits-general · gemini-2.0-flash

    I was confusing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     naturais
    -0.48
     préf
    -0.47
     käyt
    -0.44
     comerciais
    -0.44
     gosto
    -0.42
     ainfi
    -0.41
    SuppressLint
    -0.41
     käytet
    -0.40
     discussão
    -0.40
     grève
    -0.40
    POSITIVE LOGITS
    MessageTagHelper
    0.67
    featureID
    0.50
     tartalomajánló
    0.47
     '\\;'
    0.44
    ativement
    0.44
    
    0.44
     onAnimation
    0.42
     PIR
    0.41
    enterOuterAlt
    0.41
     unwittingly
    0.41
    Act Density 0.343%

    No Known Activations