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

    Neuronpedia

    INDEX
    Explanations

    cooking pot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wah
    0.48
     deluxe
    0.46
     compat
    0.46
     halal
    0.45
     unfair
    0.44
     warl
    0.43
     backup
    0.43
     rightful
    0.43
     basic
    0.43
     indir
    0.42
    POSITIVE LOGITS
    टे
    0.47
    धाम
    0.47
    시다
    0.46
    텍
    0.45
    テキスト
    0.45
    🍝
    0.44
     tomates
    0.43
    哽
    0.43
    连续
    0.43
    entation
    0.43
    Act Density 0.008%

    No Known Activations