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

    Neuronpedia

    INDEX
    Explanations

    driving rock, smart recognize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     continuing
    0.55
     بنانے
    0.53
     estancia
    0.53
     marki
    0.52
    ay
    0.52
     promesa
    0.52
     Continu
    0.51
     Keen
    0.51
    ای
    0.50
     Cic
    0.50
    POSITIVE LOGITS
    岗位
    0.52
    可以说
    0.51
    \
    0.50
    iteit
    0.49
    ísticos
    0.49
     üzere
    0.48
    takePhotoButton
    0.48
    可以说是
    0.48
    哪里
    0.48
    训练
    0.47
    Act Density 0.000%

    No Known Activations