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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions and their effectiveness in various contexts

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

    writing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CommonModule
    -0.50
     nadzieję
    -0.48
    inerja
    -0.47
    ();*/
    -0.46
    );*/
    -0.45
    tagHelperRunner
    -0.45
    });*/
    -0.44
    jsxFileName
    -0.44
    HandlerContext
    -0.43
    енча
    -0.42
    POSITIVE LOGITS
    
    0.46
    ᅠ
    0.38
    HtmlAttribute
    0.38
     propOrder
    0.36
     estekak
    0.36
    ynb
    0.35
    archiviato
    0.34
    IntoConstraints
    0.34
    GEBURTS
    0.34
    āju
    0.33
    Act Density 0.281%

    No Known Activations