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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     regarding
    -0.07
     configurations
    -0.07
     measures
    -0.07
     compatible
    -0.06
     circumference
    -0.06
     devoid
    -0.06
     Impl
    -0.06
     appar
    -0.06
    _counts
    -0.06
     Perception
    -0.06
    POSITIVE LOGITS
    uzzer
    0.07
    CSI
    0.06
    Во
    0.06
    นๆ
    0.06
     beraber
    0.06
    Tube
    0.06
     السكان
    0.06
    одатель
    0.06
     Aydın
    0.06
     ổn
    0.05
    Act Density 0.054%

    No Known Activations