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

    Neuronpedia

    INDEX
    Explanations

    they needed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ín
    0.46
    ።
    0.45
    䜌
    0.45
    íst
    0.44
    вето
    0.43
     راست
    0.42
    ís
    0.42
     caract
    0.41
    を表示
    0.41
     constancy
    0.41
    POSITIVE LOGITS
     hafif
    0.48
    സർ
    0.47
     ricordare
    0.47
     bagaimana
    0.46
    وج
    0.45
    хожу
    0.45
    remarks
    0.44
    磧
    0.43
    rocery
    0.43
    elmi
    0.42
    Act Density 0.000%

    No Known Activations