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

    Neuronpedia

    INDEX
    Explanations

    modelchecking, model, ':'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    w
    0.55
     &
    0.52
    si
    0.46
    st
    0.46
    r
    0.45
    a
    0.43
    l
    0.43
    t
    0.42
    d
    0.42
    z
    0.42
    POSITIVE LOGITS
     timeCounter
    0.53
    gramModel
    0.52
     resusc
    0.51
    𒇉
    0.49
     sowing
    0.49
     hysterical
    0.49
     ascertaining
    0.49
     paradigma
    0.49
     خفیہ
    0.48
     ہوتا
    0.48
    Act Density 0.059%

    No Known Activations