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

    Neuronpedia

    INDEX
    Explanations

    programming-related data types and structures

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

    programming data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fjspx
    -0.87
    niſſe
    -0.80
     パンチラ
    -0.80
    <unused41>
    -0.80
    <unused28>
    -0.80
    <pad>
    -0.80
    <unused14>
    -0.79
    <unused74>
    -0.79
    <unused8>
    -0.79
    <unused23>
    -0.79
    POSITIVE LOGITS
    EndGlobalSection
    0.34
     fédé
    0.34
     fonde
    0.32
     noires
    0.31
     Región
    0.31
     following
    0.30
     sanitaires
    0.27
     París
    0.27
     Hafen
    0.27
     Capitán
    0.27
    Act Density 0.008%

    No Known Activations