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

    Neuronpedia

    INDEX
    Explanations

    Kinetic Typography / suffer as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dir
    0.40
     recurs
    0.40
     dirs
    0.40
     soy
    0.40
     "//
    0.38
    lib
    0.37
     librería
    0.37
     relatives
    0.37
     sympy
    0.37
     uz
    0.36
    POSITIVE LOGITS
    لسل
    0.39
     고객
    0.39
    ्यान
    0.39
     kayaking
    0.39
     कस्टम
    0.38
    تاب
    0.38
    Cliente
    0.38
    ESTIC
    0.38
    艙
    0.38
    顾客
    0.38
    Act Density 0.000%

    No Known Activations