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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistical information about specific conditions or characteristics

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

    Numbers followed by units or measurements

    np_acts-logits-general · gemini-2.0-flash

    numbers and specific labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused43>
    -1.05
    <unused42>
    -1.05
    <unused8>
    -1.04
    <unused3>
    -1.04
    <unused16>
    -1.04
    <unused79>
    -1.04
    <unused41>
    -1.04
    <unused68>
    -1.04
    <unused23>
    -1.04
    <pad>
    -1.03
    POSITIVE LOGITS
    ↵↵
    0.79
    ↵
    0.63
    ↵↵↵
    0.58
    <eos>
    0.50
    ;
    0.46
    ↵↵↵↵
    0.43
    :
    0.42
    !
    0.41
        
    0.39
     &
    0.39
    Act Density 1.309%

    No Known Activations