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

    Neuronpedia

    INDEX
    Explanations

    ciudades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NewGuid
    0.38
    }...
    0.38
    opium
    0.38
    েও
    0.37
    Threading
    0.37
    JobList
    0.37
    冉
    0.36
    yleg
    0.36
    AvlTree
    0.36
     Zou
    0.35
    POSITIVE LOGITS
     practica
    0.47
    纪录
    0.46
    𝘤
    0.46
    られた
    0.43
     arrib
    0.43
     coat
    0.43
     coefficient
    0.42
    紀錄
    0.42
     checks
    0.40
    查
    0.39
    Act Density 0.000%

    No Known Activations