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

    Neuronpedia

    INDEX
    Explanations

    noun followed by related noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ارهای
    0.41
    urgical
    0.36
     முடியாத
    0.36
    齙
    0.36
    bär
    0.35
    പ്പെടുന്ന
    0.34
     années
    0.33
    üü
    0.33
    የ
    0.33
    糇
    0.33
    POSITIVE LOGITS
     واع
    0.37
    .”
    0.33
    𒐪
    0.33
     fortæ
    0.32
    }$.
    0.32
     क्योंकि
    0.31
     onlook
    0.31
     wors
    0.31
    respond
    0.31
     जैसा
    0.30
    Act Density 0.653%

    No Known Activations