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

    Neuronpedia

    INDEX
    Explanations

    elements related to statistical or mathematical notation and formulas

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

    Numbers, dates, and codes

    np_acts-logits-general · gemini-2.0-flash

    names and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.98
     Efq
    -0.93
    Datuak
    -0.87
    Personendaten
    -0.84
    __':
    -0.83
    ſelf
    -0.81
    RegistryLite
    -0.81
     myſelf
    -0.79
     itſelf
    -0.77
    __":
    -0.76
    POSITIVE LOGITS
    3
    0.58
    2
    0.57
    1
    0.55
    5
    0.49
    8
    0.48
    6
    0.47
    4
    0.47
    7
    0.47
    เน
    0.45
     les
    0.43
    Act Density 0.627%

    No Known Activations