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

    Neuronpedia

    INDEX
    Explanations

    adds or further effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     проми
    0.70
    轲
    0.65
    OfType
    0.65
    కున్న
    0.64
    dlj
    0.63
    खान
    0.63
     HelloWorld
    0.61
    urndata
    0.61
    HelloWorld
    0.60
     Generations
    0.59
    POSITIVE LOGITS
     further
    2.91
     exacerbate
    2.70
     exacerb
    2.60
    Further
    2.50
    further
    2.48
     Further
    2.46
    进一步
    2.45
     FURTHER
    2.34
     reinforces
    2.33
     furthering
    2.26
    Act Density 0.657%

    No Known Activations