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

    Neuronpedia

    INDEX
    Explanations

    have to, look, help, take

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ະພັນ
    0.93
    <unused95>
    0.91
    🏯
    0.91
    Bechyné
    0.90
    🕍
    0.90
    แมนเชสเตอร์ซิตี
    0.87
    🗾
    0.87
    <unused1934>
    0.86
    <unused35>
    0.86
    ຂໍ້ມ
    0.86
    POSITIVE LOGITS
    1.24
     the
    1.11
     you
    0.82
    ,
    0.79
    ↵
    0.79
     a
    0.77
     your
    0.77
    1
    0.76
    )
    0.75
     it
    0.75
    Act Density 0.000%

    No Known Activations