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

    Neuronpedia

    INDEX
    Explanations

    applying or seeing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Your
    0.97
    映
    0.95
    Your
    0.91
    、
    0.89
     Commentary
    0.89
    そして
    0.89
    原创
    0.88
    》、《
    0.87
    بین
    0.87
    。"
    0.85
    POSITIVE LOGITS
    utilisation
    1.16
    unbind
    1.12
     utilise
    1.09
     utilises
    1.07
    virk
    1.06
     brushing
    1.03
     utilising
    1.03
     utilisation
    1.03
     uses
    1.02
     milk
    1.02
    Act Density 0.000%

    No Known Activations