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

    Neuronpedia

    INDEX
    Explanations

    parts beginning with "un"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lieb
    0.53
     Müller
    0.50
     Œ
    0.50
     Slack
    0.49
     Millennials
    0.49
     Gö
    0.48
     Kü
    0.48
     Epic
    0.48
     Junk
    0.48
     Homo
    0.47
    POSITIVE LOGITS
    nte
    0.71
    ck
    0.69
    nt
    0.68
    nts
    0.68
    iminary
    0.65
    unteer
    0.63
    kében
    0.63
    ln
    0.62
    rt
    0.62
    un
    0.61
    Act Density 0.249%

    No Known Activations