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

    Neuronpedia

    INDEX
    Explanations

    point

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    took
    -0.07
    ahead
    -0.06
    Studio
    -0.06
     Crime
    -0.06
    ้้
    -0.06
    ществ
    -0.06
    щество
    -0.06
     AtomicInteger
    -0.06
    ース
    -0.06
    Crime
    -0.06
    POSITIVE LOGITS
     skillet
    0.07
     sayf
    0.07
    �
    0.07
     vmax
    0.07
    ！」
    0.06
     suger
    0.06
     Atatürk
    0.06
     maken
    0.06
    MRI
    0.06
     GS
    0.06
    Act Density 0.094%

    No Known Activations