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

    Neuronpedia

    INDEX
    Explanations

    Mathematical expressions and symbols

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

    displayed mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.89
     queſta
    -0.87
    mpagne
    -0.86
    oredCriteria
    -0.86
    rungsseite
    -0.84
    ſchaft
    -0.83
     feroit
    -0.82
    majánló
    -0.82
     ainfi
    -0.82
    <unused68>
    -0.81
    POSITIVE LOGITS
    $$\
    0.67
    displaystyle
    0.60
    $$
    0.54
    y
    0.50
    <td>
    0.48
    $\
    0.45
    <code>
    0.45
    $
    0.43
    0.42
    0.42
    Act Density 0.056%

    No Known Activations