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

    Neuronpedia

    INDEX
    Explanations

    keywords related to programming models and scripts

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

    model definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zzleHttp
    -0.40
    __*/
    -0.34
     derajat
    -0.30
    Архівовано
    -0.30
    TagMode
    -0.29
     ddelweddau
    -0.29
    StoryboardSegue
    -0.28
     correto
    -0.28
    PointerException
    -0.28
    ::*;
    -0.28
    POSITIVE LOGITS
    model
    1.06
     model
    1.02
     MODEL
    0.92
     Model
    0.91
    MODEL
    0.88
    モデル
    0.84
     models
    0.82
     Models
    0.82
     modeled
    0.79
    getModel
    0.79
    Act Density 0.000%

    No Known Activations