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

    Neuronpedia

    INDEX
    Explanations

    sequences of whitespace or line breaks in the text

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

    code structure keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.51
     itſelf
    -0.50
     faſt
    -0.46
    wiſe
    -0.45
    /*
    -0.44
     оригіналу
    -0.42
    Abitanti
    -0.42
    contentLoaded
    -0.42
     ſa
    -0.41
    处
    -0.41
    POSITIVE LOGITS
    ConstraintMaker
    0.57
    HomeAsUpEnabled
    0.49
    ResumeLayout
    0.49
    colgante
    0.46
    bootstrapcdn
    0.46
    
    0.46
     InputDecoration
    0.46
    UnusedPrivate
    0.45
    transQ
    0.45
    rinfo
    0.44
    Act Density 0.017%

    No Known Activations