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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    नंतर
    0.79
     झाल्यावर
    0.73
     getServer
    0.72
     після
    0.71
     различни
    0.71
     україн
    0.71
     белару
    0.70
    。
    0.70
    ،
    0.69
    以后
    0.69
    POSITIVE LOGITS
     Ng
    0.81
    Error
    0.80
    culture
    0.79
    PG
    0.78
    POLY
    0.76
    PK
    0.75
    PC
    0.73
     প্রস্তুতি
    0.73
    rival
    0.72
    ord
    0.71
    Act Density 0.003%

    No Known Activations