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

    Neuronpedia

    INDEX
    Explanations

    Spring Boot and Spring Cloud dependencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    siehe
    2.03
    و
    1.90
     karde
    1.79
    ►
    1.78
    सी
    1.70
     grosse
    1.68
    Ко
    1.67
     fiind
    1.64
     carreteras
    1.64
    en
    1.63
    POSITIVE LOGITS
    chainId
    1.93
    𝐛
    1.88
    𝐞
    1.76
    𝐦
    1.76
    DID
    1.74
    𝐮
    1.73
    erness
    1.70
    manship
    1.69
    𝐲
    1.69
    widetilde
    1.65
    Act Density 0.001%

    No Known Activations