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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming constructs and control flow

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

    code block starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.35
     adquirido
    -0.34
    :✨
    -0.34
     myö
    -0.33
    Derbyniad
    -0.33
    mappedBy
    -0.32
    popd
    -0.31
    Autoritní
    -0.31
     delà
    -0.30
    MLLoader
    -0.30
    POSITIVE LOGITS
     ſind
    0.59
    SequentialGroup
    0.56
    RTEX
    0.54
     durs
    0.54
     للمعارف
    0.52
     informant
    0.51
    wiliwch
    0.51
    ագրություններ
    0.50
    endphp
    0.50
     dieſes
    0.50
    Act Density 0.009%

    No Known Activations