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

    Neuronpedia

    INDEX
    Explanations

    emphasis markers such as italics and bold formatting

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

    html emphasis tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.86
     betweenstory
    -0.85
    IntoConstraints
    -0.74
    WebElementEntity
    -0.73
     desmotivaciones
    -0.73
    Bakgrunnsstoff
    -0.72
    colgante
    -0.71
     ſind
    -0.70
    ſcher
    -0.69
    DockStyle
    -0.69
    POSITIVE LOGITS
    <em>
    1.98
    <i>
    1.80
    <strong>
    1.10
    <u>
    1.09
    <b>
    1.05
    /*
    0.90
    <code>
    0.84
    <sub>
    0.81
    <h3>
    0.77
    __(/*!
    0.73
    Act Density 0.000%

    No Known Activations