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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly those representing ages or quantities

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

    numbers followed by units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    참고
    -0.54
    s
    -0.54
    ်
    -0.47
    IC
    -0.46
    2
    -0.46
    FC
    -0.45
    n
    -0.44
    0
    -0.43
    R
    -0.42
    RC
    -0.41
    POSITIVE LOGITS
     Verſ
    0.93
     plufieurs
    0.85
     ſeveral
    0.81
     seventeen
    0.77
     ſind
    0.77
     camiset
    0.75
     nineteen
    0.73
     fourteen
    0.73
     fifteen
    0.71
     sixteen
    0.71
    Act Density 0.007%

    No Known Activations