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

    Neuronpedia

    INDEX
    Explanations

    numerical values or quantities in the text

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

    numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administración
    -0.45
    ,
    -0.43
     Ausnahme
    -0.42
     Administração
    -0.41
    .
    -0.40
    The
    -0.40
     following
    -0.39
     Außerdem
    -0.38
     Dabei
    -0.37
     Allerdings
    -0.37
    POSITIVE LOGITS
    <unused79>
    0.72
    <unused16>
    0.72
    <unused68>
    0.71
    <unused3>
    0.71
    <unused42>
    0.71
    <unused41>
    0.71
    <unused43>
    0.71
    <unused28>
    0.71
    <unused8>
    0.71
    <unused17>
    0.71
    Act Density 0.133%

    No Known Activations