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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ndetse
    -0.09
     прид
    -0.08
     vile
    -0.08
     તેમજ
    -0.08
     Strap
    -0.08
     cardí
    -0.08
    ]).↵
    -0.08
     декабря
    -0.08
     Histogram
    -0.08
     свят
    -0.07
    POSITIVE LOGITS
     memories
    0.10
     emotions
    0.09
     subconscious
    0.09
     opinions
    0.09
     memoir
    0.08
     imagination
    0.08
     mindfulness
    0.08
     현실
    0.08
     metaphor
    0.08
     euros
    0.08
    Act Density 0.076%

    No Known Activations