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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     땅
    -0.06
     vign
    -0.06
     zem
    -0.06
     конф
    -0.06
     tinh
    -0.06
    GNU
    -0.06
    TableRow
    -0.05
     Trần
    -0.05
     Ptr
    -0.05
     Generated
    -0.05
    POSITIVE LOGITS
     inflater
    0.06
    ossip
    0.06
    -call
    0.06
     Mondays
    0.06
    ادث
    0.06
     Luke
    0.06
    ruk
    0.06
     elite
    0.06
     invert
    0.06
    '"
    0.06
    Act Density 0.000%

    No Known Activations