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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    内
    -0.07
     irritating
    -0.07
    expo
    -0.07
     impres
    -0.07
     chubby
    -0.07
     instrument
    -0.07
     edilmesi
    -0.07
     judgment
    -0.06
    rapid
    -0.06
     oxide
    -0.06
    POSITIVE LOGITS
    くな
    0.07
     فإن
    0.07
     회사
    0.07
    itbart
    0.06
    /send
    0.06
    (Parcel
    0.06
    Canceled
    0.06
    ctrl
    0.06
     gửi
    0.06
        
    0.06
    Act Density 0.086%

    No Known Activations