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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    疑
    -0.07
     HL
    -0.07
    評
    -0.07
     comparative
    -0.06
     kop
    -0.06
     receipt
    -0.06
     Comparative
    -0.06
     consists
    -0.06
    BitConverter
    -0.06
    Scoped
    -0.06
    POSITIVE LOGITS
    umlu
    0.07
     уси
    0.07
    .students
    0.06
     мне
    0.06
    REFER
    0.06
    的小
    0.06
     motions
    0.06
     лов
    0.06
    -toast
    0.06
    větší
    0.06
    Act Density 0.042%

    No Known Activations