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

    Neuronpedia

    INDEX
    Explanations

    units and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dismiss
    0.46
    Dismiss
    0.45
    0.45
     *
    0.41
     >
    0.40
     Redis
    0.38
    README
    0.37
     “
    0.37
     Dile
    0.37
    Yet
    0.37
    POSITIVE LOGITS
     rebounding
    0.53
    চ্ছন্দ
    0.51
     scoring
    0.51
    counterx
    0.47
    TGFuZ
    0.47
     cleats
    0.47
    ।-
    0.47
     GARC
    0.47
    ەل
    0.46
     drm
    0.45
    Act Density 0.001%

    No Known Activations