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

    Neuronpedia

    INDEX
    Explanations

    technical or code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uvwxyz
    0.72
    Visualization
    0.69
     quitting
    0.69
    boosting
    0.66
    ñada
    0.65
    山
    0.65
    edge
    0.65
    zero
    0.65
    படுத்த
    0.65
     appreciating
    0.64
    POSITIVE LOGITS
     Candid
    0.81
     Ples
    0.78
     subsystem
    0.78
     आतंकियों
    0.77
     plenum
    0.76
    牖
    0.74
     Xun
    0.73
     scalars
    0.73
     Cun
    0.69
    unan
    0.68
    Act Density 0.000%

    No Known Activations