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

    Neuronpedia

    INDEX
    Explanations

    LaTeX syntax elements and structures

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

    Mathematical expressions and symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -1.16
    ſelves
    -1.12
     myſelf
    -1.11
     iſt
    -1.10
     ſind
    -1.08
     pleaſure
    -1.08
     Anſ
    -1.07
     purpoſe
    -1.04
    ſelf
    -1.03
     Theſe
    -1.02
    POSITIVE LOGITS
     
    0.57
     -
    0.51
     Verpflichtung
    0.50
    ">
    0.49
    v
    0.49
     conseils
    0.47
    E
    0.47
      
    0.46
    m
    0.46
    <unused61>
    0.46
    Act Density 0.017%

    No Known Activations