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

    Neuronpedia

    INDEX
    Explanations

    original

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .offsetWidth
    -0.06
     scattering
    -0.06
     sheet
    -0.05
    avors
    -0.05
     belts
    -0.05
     boxes
    -0.05
    -transition
    -0.05
    出口
    -0.05
    (".")
    -0.05
     сегодня
    -0.05
    POSITIVE LOGITS
     ortalama
    0.07
    È
    0.07
    vla
    0.07
     serialize
    0.07
    .theta
    0.07
    ekkür
    0.07
    Records
    0.07
     observational
    0.06
    lessons
    0.06
    ekl
    0.06
    Act Density 0.003%

    No Known Activations