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

    Neuronpedia

    INDEX
    Explanations

    cross again

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    न
    0.55
    ண்ண
    0.54
    多くの
    0.52
     amacı
    0.51
    す
    0.49
    ल
    0.48
     conco
    0.48
    น
    0.48
    ဝ
    0.48
     artworks
    0.47
    POSITIVE LOGITS
     ergeben
    0.48
     Initially
    0.45
    प्ति
    0.43
    明显
    0.43
    legenheit
    0.42
     Alternatively
    0.41
    你自己
    0.40
    statistik
    0.40
    temperatur
    0.39
    phus
    0.39
    Act Density 0.000%

    No Known Activations