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

    Neuronpedia

    INDEX
    Explanations

    Gamma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     content
    -0.08
     הת
    -0.07
    lined
    -0.07
     relev
    -0.07
     lease
    -0.07
    TV
    -0.07
    ตาม
    -0.07
     retrieved
    -0.07
    أخبار
    -0.06
    jej
    -0.06
    POSITIVE LOGITS
     ############
    0.08
     Kerala
    0.07
    云端
    0.07
    (set
    0.07
    全世界
    0.07
    _protocol
    0.07
    —including
    0.07
     NUM
    0.07
    _roll
    0.07
     //////
    0.07
    Act Density 0.002%

    No Known Activations