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

    Neuronpedia

    INDEX
    Explanations

    unlike traditional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RC
    0.46
     ல
    0.44
     আমার
    0.43
    আমি
    0.42
     avoid
    0.42
     моей
    0.41
    私の
    0.41
    一
    0.40
    accessory
    0.40
    他
    0.40
    POSITIVE LOGITS
     brunes
    0.55
     berper
    0.55
    ClearedBy
    0.54
     Kamane
    0.48
     beragam
    0.46
    CameraOpened
    0.45
     ory
    0.44
     ಸಾಮಾನ್ಯವಾಗಿ
    0.44
    atthena
    0.44
    맷
    0.44
    Act Density 0.000%

    No Known Activations