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

    Neuronpedia

    INDEX
    Explanations

    java package imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inclination
    0.88
     slanted
    0.78
     clipped
    0.77
     tendency
    0.77
    MACl
    0.77
     tendencies
    0.77
     البط
    0.76
     FAQs
    0.76
    Chaos
    0.76
     instabilities
    0.75
    POSITIVE LOGITS
     org
    1.86
     com
    1.68
    org
    1.66
     java
    1.47
     lombok
    1.40
     javax
    1.35
    com
    1.29
     androidx
    1.21
     io
    1.21
     jakarta
    1.17
    Act Density 0.003%

    No Known Activations