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

    Neuronpedia

    INDEX
    Explanations

    expressions related to programming structures and operations, particularly in Java

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

    loop index `i`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zijne
    -0.38
     suaminya
    -0.36
     mijne
    -0.32
     hendes
    -0.32
    pherals
    -0.31
    setContentView
    -0.31
     biela
    -0.30
     küche
    -0.30
    PhysRev
    -0.30
     Grüsse
    -0.30
    POSITIVE LOGITS
     objectAtIndex
    0.58
     Wartawan
    0.51
    extAlignment
    0.51
     विश्वसनीयता
    0.49
     $_[
    0.49
     Fits
    0.48
    Fits
    0.48
    tshell
    0.48
     IndexError
    0.48
    Datuak
    0.48
    Act Density 0.181%

    No Known Activations