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

    Neuronpedia

    INDEX
    Explanations

    fitting with tests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resemble
    0.48
    ApiKey
    0.45
    𝗦
    0.45
    ܕ
    0.43
     irritable
    0.43
     carbs
    0.42
    Synchron
    0.42
    Shape
    0.41
    初の
    0.41
     contains
    0.41
    POSITIVE LOGITS
    テスト
    0.49
     éstos
    0.47
    <0x88>
    0.45
    ifty
    0.45
     جاس
    0.45
     राह
    0.45
     बातों
    0.44
     ave
    0.44
     éviter
    0.44
    اکہ
    0.43
    Act Density 0.002%

    No Known Activations