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

    Neuronpedia

    INDEX
    Explanations

    file systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     библиоте
    0.39
     äuß
    0.39
     top
    0.38
    pellier
    0.37
     planche
    0.37
    imus
    0.36
    ❜
    0.36
     begg
    0.36
     Kxf
    0.36
    finger
    0.36
    POSITIVE LOGITS
     fs
    0.62
     FS
    0.61
     FSC
    0.61
     فس
    0.55
    ociety
    0.54
     FSB
    0.50
     FSA
    0.49
    FS
    0.46
     BFS
    0.46
    فس
    0.45
    Act Density 0.007%

    No Known Activations