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

    Neuronpedia

    INDEX
    Explanations

    references to supplementary material and appendixes in academic texts

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

    supplementary appendix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.55
    AndroidJUnit
    -0.42
    PerformLayout
    -0.42
     tez
    -0.41
    PreferredItem
    -0.41
    delwed
    -0.41
     unknownFields
    -0.40
     Signalez
    -0.40
    tagHelperRunner
    -0.40
     surrendered
    -0.40
    POSITIVE LOGITS
     Frist
    0.45
     مشارکت‌کنندگان
    0.42
    igeon
    0.40
    theguardian
    0.40
    LAUGHTER
    0.40
    पया
    0.38
     PeEnEo
    0.37
    ALLES
    0.37
    хьтан
    0.36
    óta
    0.36
    Act Density 0.106%

    No Known Activations