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

    Neuronpedia

    INDEX
    Explanations

    characteristics and qualities of narratives and characters in various contexts

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

    romance between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.69
     defaultstate
    -0.60
     BoxFit
    -0.56
    IsPostBack
    -0.55
    InjectAttribute
    -0.54
    IContainer
    -0.54
     mergeFrom
    -0.54
     BorderSide
    -0.53
    phosa
    -0.53
    InjectMocks
    -0.51
    POSITIVE LOGITS
     nice
    0.33
     Nice
    0.29
     bonne
    0.28
    确实是
    0.28
    確實
    0.28
     nombreuses
    0.28
     though
    0.27
     bonnes
    0.27
    łki
    0.27
     ellers
    0.27
    Act Density 0.032%

    No Known Activations