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

    Neuronpedia

    INDEX
    Explanations

    numerical values and monetary symbols

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

    LaTeX math and table environments

    np_acts-logits-general · gemini-2.0-flash

    LaTeX math and tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    -0.57
     modern
    -0.56
    !#
    -0.53
    ########.
    -0.52
    pecially
    -0.49
    jina
    -0.47
    #!/
    -0.47
     real
    -0.47
     arti
    -0.46
     mor
    -0.46
    POSITIVE LOGITS
    AndEndTag
    1.01
    tvguidetime
    1.00
    </td>
    0.90
    ConstraintMaker
    0.84
    ագրություններ
    0.81
     الحره
    0.81
    DockStyle
    0.79
    IntoConstraints
    0.76
    TestingModule
    0.75
    BeginInit
    0.74
    Act Density 0.314%

    No Known Activations