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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the character '{' indicating the start of code blocks or object definitions

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

    code and programming methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SBATCH
    -0.40
    jutnya
    -0.39
     Polres
    -0.39
    uangan
    -0.38
    rungsseite
    -0.38
     tapes
    -0.37
     Vikipedi
    -0.37
    SerializeField
    -0.37
    жнему
    -0.36
    CJK
    -0.35
    POSITIVE LOGITS
     surla
    0.59
    MessageOf
    0.52
    IsContent
    0.45
    ək
    0.43
     CURLOPT
    0.42
    setViewportView
    0.41
     Rid
    0.40
    trane
    0.40
     Lever
    0.39
     setLoading
    0.39
    Act Density 0.005%

    No Known Activations