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

    Neuronpedia

    INDEX
    Explanations

    pay for stock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.03
    n
    0.98
    en
    0.86
    om
    0.78
    er
    0.77
    َ
    0.75
    loro
    0.75
    es
    0.74
    id
    0.73
    ez
    0.73
    POSITIVE LOGITS
     wreaths
    0.97
     wreak
    0.88
     decimated
    0.87
     trellis
    0.84
     BDS
    0.82
     notch
    0.80
     notches
    0.79
    ftime
    0.79
     eigenfunctions
    0.79
     kms
    0.79
    Act Density 0.000%

    No Known Activations