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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bbs
    -0.08
     Bubble
    -0.07
     diter
    -0.07
     ਪ
    -0.07
     прост
    -0.07
     pojed
    -0.07
    ibon
    -0.07
     ਗ
    -0.07
    _apps
    -0.07
    ાત્મક
    -0.07
    POSITIVE LOGITS
     比
    0.12
     श्रेष्ठ
    0.11
    比
    0.11
     inferior
    0.10
    Compared
    0.10
     northeast
    0.10
     ఎక్కువ
    0.10
     نسبت
    0.10
    iore
    0.09
     superiority
    0.09
    Act Density 0.049%

    No Known Activations