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

    Neuronpedia

    INDEX
    Explanations

    reversals or opposite sides

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     올라
    -0.06
    abela
    -0.06
     Cham
    -0.06
    ایی
    -0.06
     Namen
    -0.06
    .stereotype
    -0.06
     cas
    -0.06
    host
    -0.06
    робіт
    -0.06
    Submitting
    -0.06
    POSITIVE LOGITS
     sets
    0.06
    _purchase
    0.06
    _trip
    0.06
     Purch
    0.06
     *\
    0.06
    	Query
    0.06
     ',
    0.06
    .Sequence
    0.06
    0.06
    ,L
    0.06
    Act Density 0.121%

    No Known Activations