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

    Neuronpedia

    INDEX
    Explanations

    option or choice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pools
    0.41
     createElement
    0.38
     дітей
    0.38
     USP
    0.37
     RouterModule
    0.37
    폴
    0.36
     seizing
    0.36
     Pools
    0.36
     pool
    0.36
     제목
    0.36
    POSITIVE LOGITS
    option
    0.53
     opção
    0.49
    オプション
    0.47
     opción
    0.45
    envs
    0.45
     opciones
    0.42
    ॉर
    0.40
     actitudes
    0.39
     Option
    0.39
     вариант
    0.39
    Act Density 0.000%

    No Known Activations