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

    Neuronpedia

    INDEX
    Explanations

    instances of import statements in programming code

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

    package declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    -0.41
    v
    -0.40
    en
    -0.36
    able
    -0.35
    ty
    -0.35
    ta
    -0.35
    ↵
    -0.34
    <eos>
    -0.33
    ph
    -0.33
     
    -0.33
    POSITIVE LOGITS
    ftagPool
    1.10
     للمعارف
    1.07
    <unused43>
    1.05
    <unused41>
    1.05
    <unused14>
    1.05
    <unused8>
    1.05
    <unused16>
    1.05
    <unused17>
    1.05
    [@BOS@]
    1.05
    <unused3>
    1.05
    Act Density 0.001%

    No Known Activations