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

    Neuronpedia

    INDEX
    Explanations

    code and structured text delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intron
    0.41
     inelastic
    0.38
     serene
    0.38
     entrou
    0.38
     ranc
    0.38
     anten
    0.37
     inf
    0.37
     papp
    0.37
     mes
    0.37
     appendices
    0.37
    POSITIVE LOGITS
    <h3>
    0.44
    {
    0.38
    $\
    0.37
    <td>
    0.37
     गौरतलब
    0.35
    Если
    0.35
    இது
    0.34
    ሁሉም
    0.32
    ial
    0.32
    ipher
    0.32
    Act Density 0.000%

    No Known Activations