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

    Neuronpedia

    INDEX
    Explanations

    filter and permissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    insulated
    1.35
    стройка
    1.33
     pente
    1.32
    Posture
    1.31
     vite
    1.30
    ب
    1.29
     टू
    1.26
     reverb
    1.25
     preuve
    1.25
     communion
    1.24
    POSITIVE LOGITS
    ষ্ঠ
    1.39
    <td>
    1.36
    रों
    1.36
    AN
    1.35
    an
    1.32
    ąd
    1.29
    tif
    1.26
    ان
    1.25
    本セット
    1.25
    GEO
    1.23
    Act Density 0.000%

    No Known Activations