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

    Neuronpedia

    INDEX
    Explanations

    finding by id

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    2.45
    ه
    2.38
    𝐁
    2.18
    이
    2.09
     mathbf
    2.03
    هي
    1.96
    संख्या
    1.93
    ర్చు
    1.90
    𝐒
    1.88
     tf
    1.88
    POSITIVE LOGITS
    াসে
    1.77
     próximo
    1.53
    ieurs
    1.52
    р
    1.51
     yönelik
    1.48
     invigorating
    1.48
    teenth
    1.46
     abode
    1.45
     узнать
    1.45
     grü
    1.44
    Act Density 0.000%

    No Known Activations