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

    Neuronpedia

    INDEX
    Explanations

    seafood

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sedan
    -0.07
    帽
    -0.07
    ResponseStatus
    -0.07
    房企
    -0.07
    (Convert
    -0.07
    绿水
    -0.06
    ders
    -0.06
    CheckBox
    -0.06
    ListAdapter
    -0.06
    ifiers
    -0.06
    POSITIVE LOGITS
    Ze
    0.07
     ment
    0.07
    的认可
    0.07
    ክ
    0.07
     Etsy
    0.07
     ................
    0.06
    IBAction
    0.06
     generous
    0.06
     Blo
    0.06
    sar
    0.06
    Act Density 0.095%

    No Known Activations