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

    Neuronpedia

    INDEX
    Explanations

    symbols and syntax related to data structures or arrays

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

    user input or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    -0.31
     the
    -0.30
     (
    -0.28
    ↵↵
    -0.28
     qu
    -0.27
     \
    -0.26
     f
    -0.26
     h
    -0.26
      
    -0.25
     y
    -0.24
    POSITIVE LOGITS
    majánló
    1.13
    <unused79>
    1.10
    <unused43>
    1.10
    <unused52>
    1.10
    <unused16>
    1.10
    <unused14>
    1.10
    <unused23>
    1.10
    <unused51>
    1.10
    <unused28>
    1.10
    <pad>
    1.09
    Act Density 0.002%

    No Known Activations