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

    Neuronpedia

    INDEX
    Explanations

    Number suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nurture
    -0.06
     spanking
    -0.06
    ought
    -0.06
     lin
    -0.06
    從
    -0.06
     Get
    -0.06
     holder
    -0.06
     Anthem
    -0.06
     holding
    -0.06
    [color
    -0.06
    POSITIVE LOGITS
    еним
    0.07
    σίας
    0.07
    pop
    0.07
    πί
    0.07
    Pop
    0.06
    \uB
    0.06
    _prime
    0.06
    "}),↵
    0.06
    ��
    0.06
     Clips
    0.06
    Act Density 0.072%

    No Known Activations