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

    Neuronpedia

    INDEX
    Explanations

    eventually, time, someday, line

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     virtualization
    0.46
     playable
    0.42
     trimester
    0.42
     hemodynamic
    0.40
     simplistic
    0.40
     radiative
    0.38
     virulence
    0.38
    ริ
    0.38
     geriatric
    0.38
     sikre
    0.38
    POSITIVE LOGITS
    o
    0.77
    c
    0.67
    y
    0.61
    r
    0.57
    n
    0.56
    h
    0.56
    t
    0.55
    l
    0.52
    e
    0.51
    v
    0.50
    Act Density 0.246%

    No Known Activations