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

    Neuronpedia

    INDEX
    Explanations

    represent / representaciones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    غ
    0.52
    اء
    0.51
    ayısıyla
    0.49
    ')]
    0.49
    StubCompat
    0.46
    اوی
    0.46
    ну
    0.45
    سة
    0.45
    гра
    0.45
     Grac
    0.45
    POSITIVE LOGITS
    Who
    0.54
    Believe
    0.53
    ONE
    0.52
    ILL
    0.51
    ᖇ
    0.51
    ₮
    0.50
    Addressing
    0.50
    ING
    0.50
    Organizations
    0.49
    Run
    0.48
    Act Density 0.000%

    No Known Activations