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

    Neuronpedia

    INDEX
    Explanations

    numbers and words indicating quantity or being one of multiple.

    oai_token-act-pair · gemini-2.0-flash

    small quantities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.75
    DebuggerNonUser
    -0.74
    sizeCache
    -0.71
    fjspx
    -0.70
    اریخ
    -0.69
     tartalomajánló
    -0.69
     propOrder
    -0.68
    цездатний
    -0.66
    minecraftforge
    -0.65
    存于互联网档案馆
    -0.65
    POSITIVE LOGITS
    <
    0.47
    '
    0.46
    ="#"><
    0.44
    rindo
    0.43
     ===
    0.43
    NP
    0.42
    accesso
    0.41
     ")[
    0.41
     benne
    0.41
    lanmış
    0.41
    Act Density 22.274%

    No Known Activations