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

    Neuronpedia

    INDEX
    Explanations

    assistance with code and creative tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    petite
    0.55
    porque
    0.55
    finaly
    0.53
     ابي
    0.53
    िनेट
    0.51
    instrList
    0.51
    trx
    0.51
    thisComponent
    0.51
     Потому
    0.51
    ScienceStudent
    0.51
    POSITIVE LOGITS
    i
    0.74
    y
    0.68
     i
    0.68
    S
    0.68
    u
    0.67
    X
    0.66
    T
    0.64
    C
    0.59
     and
    0.59
    W
    0.58
    Act Density 0.353%

    No Known Activations