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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and syntactic structures related to defining variables and their types

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

    enums and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused79>
    -0.89
    <unused52>
    -0.89
    <unused17>
    -0.89
    <unused8>
    -0.89
    <unused68>
    -0.89
    <unused23>
    -0.89
    <unused51>
    -0.89
    <unused28>
    -0.89
    <unused14>
    -0.89
    <unused16>
    -0.89
    POSITIVE LOGITS
     choice
    0.43
     chosen
    0.36
     despla
    0.33
    Enumerated
    0.31
     choose
    0.30
     scelta
    0.30
     selected
    0.29
     type
    0.29
     Figueroa
    0.29
     is
    0.28
    Act Density 0.012%

    No Known Activations