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

    Neuronpedia

    INDEX
    Explanations

    introductory phrases with colon-asterisk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    0.76
    inside
    0.72
    dalam
    0.69
     kembali
    0.67
     pembang
    0.65
    ם
    0.64
    ו
    0.64
    ز
    0.63
    प
    0.61
     serta
    0.61
    POSITIVE LOGITS
    qos
    0.76
    ;:
    0.70
    :
    0.67
    ]:
    0.65
    कारों
    0.65
    🇽
    0.64
    IZONTAL
    0.64
    ))
    0.64
    ټبال
    0.63
    人士
    0.62
    Act Density 0.624%

    No Known Activations