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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to digital or analog signal processing and conversion

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

    Binary code and bits

    np_acts-logits-general · gemini-2.0-flash

    binary bit representation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __((
    -0.64
     externi
    -0.58
    skraft
    -0.54
    Autoritní
    -0.52
     localObject
    -0.51
    avons
    -0.51
    inence
    -0.50
     Malden
    -0.49
    RTLI
    -0.48
     <>",
    -0.48
    POSITIVE LOGITS
     bit
    1.20
     binary
    1.16
    bit
    1.05
     Bit
    1.03
    Bit
    0.99
    binary
    0.97
     Binary
    0.97
    Binary
    0.93
     bits
    0.93
     encoded
    0.92
    Act Density 0.993%

    No Known Activations