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

    Neuronpedia

    INDEX
    Explanations

    code-related elements in a programming context

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

    Code or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    width attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.55
    ri
    -0.53
    om
    -0.49
    al
    -0.48
    ci
    -0.45
    a
    -0.45
    it
    -0.45
    ir
    -0.44
    ла
    -0.43
    <strong>
    -0.42
    POSITIVE LOGITS
     ddelweddau
    1.25
    //
    1.08
    IntoConstraints
    1.06
    UserScript
    1.05
    ⓧ
    0.99
     Wiktionnaire
    0.98
    ThroughAttribute
    0.98
    <?
    0.96
    PerformLayout
    0.96
    InjectAttribute
    0.92
    Act Density 1.693%

    No Known Activations