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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Čes
    -0.07
     FHA
    -0.07
    Crop
    -0.06
    ินท
    -0.06
    Ted
    -0.06
     Maher
    -0.06
    Mate
    -0.06
     '%
    -0.06
    Pu
    -0.06
    icate
    -0.06
    POSITIVE LOGITS
    pository
    0.07
     iterable
    0.06
    &M
    0.06
     bilateral
    0.06
     trials
    0.06
     …↵
    0.06
    ishop
    0.06
    ...↵
    0.06
     Shepherd
    0.06
     scenery
    0.06
    Act Density 0.273%

    No Known Activations