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

    Neuronpedia

    INDEX
    Explanations

    Hebrew

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    724
    -0.07
    スの
    -0.07
    ़ी
    -0.07
    >'
    -0.06
    069
    -0.06
    раль
    -0.06
    ordon
    -0.06
    ussen
    -0.06
     Four
    -0.06
    -more
    -0.06
    POSITIVE LOGITS
    נ
    0.07
     wherein
    0.06
     overlaps
    0.06
     undergrad
    0.06
     existed
    0.06
     sophistic
    0.06
    Async
    0.06
    .md
    0.06
     gerektir
    0.06
     ayn
    0.06
    Act Density 0.023%

    No Known Activations