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

    Neuronpedia

    INDEX
    Explanations

    understanding you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     any
    0.81
     alred
    0.74
    υτό
    0.68
     quaisquer
    0.67
    any
    0.66
     ANY
    0.66
     theses
    0.65
     NgModule
    0.65
     resumes
    0.64
    또한
    0.64
    POSITIVE LOGITS
    。。。
    0.87
    কারীর
    0.84
    Panning
    0.82
     Zach
    0.82
     capitalizing
    0.81
     التأ
    0.81
    Deletion
    0.81
     exemplu
    0.81
     অনুরোধ
    0.80
     favoring
    0.80
    Act Density 0.050%

    No Known Activations