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

    Neuronpedia

    INDEX
    Explanations

    logarithmic scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Adri
    0.68
     দেরী
    0.68
     Josiah
    0.67
     dépôt
    0.65
     Aktiv
    0.65
     csrf
    0.64
    હિતી
    0.63
     itth
    0.63
    ိမ်
    0.63
     cookie
    0.63
    POSITIVE LOGITS
     scale
    4.73
     Scale
    4.50
    Scale
    4.39
     scales
    4.37
     scaling
    4.35
    scale
    4.32
    Scal
    4.21
     Scaling
    4.08
    Scaling
    4.02
     Scal
    4.00
    Act Density 0.302%

    No Known Activations