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

    Neuronpedia

    INDEX
    Explanations

    TPO targets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.61
    azole
    0.48
    vär
    0.46
    f
    0.46
    ส
    0.46
    SP
    0.45
    <start_of_image>
    0.45
    canc
    0.45
    carbonyl
    0.44
     ===
    0.43
    POSITIVE LOGITS
    ສາມາດ
    0.54
     medit
    0.52
     particulares
    0.51
     می‌توان
    0.49
    चुरल
    0.48
     নিয়োগ
    0.47
     transactions
    0.46
    式の
    0.46
     patho
    0.46
     کیسے
    0.46
    Act Density 0.000%

    No Known Activations