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

    Neuronpedia

    INDEX
    Explanations

    questions or queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rewarded
    0.39
     delightful
    0.38
     wonderful
    0.38
     magnificent
    0.37
     beautiful
    0.37
     fabulous
    0.36
    素敵な
    0.36
    The
    0.36
     Delaware
    0.35
     celebró
    0.35
    POSITIVE LOGITS
    ถาม
    0.45
    ページ
    0.44
    髹
    0.44
     तो
    0.43
    ם
    0.43
     spør
    0.43
    প্রশ্ন
    0.42
     Queries
    0.42
    閒
    0.42
    睒
    0.41
    Act Density 0.000%

    No Known Activations