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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their contexts within sentences

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

    user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſſung
    -0.88
    niſſe
    -0.88
     चीज़ों
    -0.82
    ſchaft
    -0.82
     Waſſer
    -0.82
    enablog
    -0.81
     zuſammen
    -0.81
    ஦
    -0.81
     Geiſt
    -0.81
     MainAxisSize
    -0.80
    POSITIVE LOGITS
    s
    0.57
     
    0.39
     <
    0.38
    belongsTo
    0.36
    <
    0.36
    model
    0.36
    N
    0.35
    //
    0.34
    ↵
    0.33
     N
    0.33
    Act Density 0.000%

    No Known Activations