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

    Neuronpedia

    INDEX
    Explanations

    don't rush, be authentic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wavelet
    0.35
     disks
    0.34
     obtains
    0.34
     obtain
    0.34
     vesicular
    0.33
     assorted
    0.33
     tunic
    0.32
     vesicles
    0.31
     vesicle
    0.31
     strict
    0.31
    POSITIVE LOGITS
     don
    0.55
    Everyone
    0.52
     Don
    0.51
     Believe
    0.51
    Believe
    0.51
    Your
    0.50
     Nobody
    0.50
     Chances
    0.50
    Nobody
    0.49
     YOUR
    0.49
    Act Density 0.080%

    No Known Activations