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

    Neuronpedia

    INDEX
    Explanations

    inventions and findings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     true
    -0.07
     called
    -0.07
    执行
    -0.07
    して
    -0.07
    ourd
    -0.07
     lifestyle
    -0.06
     '?'
    -0.06
    contrast
    -0.06
    _____
    -0.06
    552
    -0.06
    POSITIVE LOGITS
    	bs
    0.06
     ❤
    0.06
     stitches
    0.06
    τομα
    0.06
    ...");↵↵
    0.06
    _PCI
    0.06
     mệnh
    0.06
     captures
    0.06
     δυνα
    0.06
    PX
    0.06
    Act Density 0.011%

    No Known Activations