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

    Neuronpedia

    INDEX
    Explanations

    Population statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ข
    -0.07
    .LOC
    -0.07
    =(-
    -0.07
    жно
    -0.06
    _AR
    -0.06
     травня
    -0.06
    validate
    -0.06
     státy
    -0.06
     paradox
    -0.06
    .rb
    -0.06
    POSITIVE LOGITS
     stylish
    0.07
     chic
    0.06
     popularity
    0.06
     falls
    0.06
    OrDefault
    0.06
     tersebut
    0.06
    _PRICE
    0.06
     RAID
    0.06
     takes
    0.06
    _bases
    0.06
    Act Density 0.000%

    No Known Activations