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

    Neuronpedia

    INDEX
    Explanations

    html for web pages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     szere
    0.40
     $\
    0.40
     owing
    0.39
     hereby
    0.38
     \
    0.37
     factorial
    0.36
     Flores
    0.36
     Moines
    0.36
     menyatakan
    0.34
     reported
    0.34
    POSITIVE LOGITS
     halfCanvas
    0.48
     పోలీసు
    0.46
    Innovative
    0.46
    系统的
    0.45
     ZONE
    0.45
    ()<
    0.45
    Diverse
    0.44
    Modal
    0.44
    थाम
    0.44
     cGraph
    0.43
    Act Density 0.001%

    No Known Activations