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

    Neuronpedia

    INDEX
    Explanations

    filter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Giá
    -0.08
    	Initialize
    -0.07
     IService
    -0.07
     uğra
    -0.07
    Kat
    -0.07
     Eva
    -0.07
     Kob
    -0.06
    etails
    -0.06
    trx
    -0.06
     citizenship
    -0.06
    POSITIVE LOGITS
    \)
    0.08
    �
    0.07
     victories
    0.06
     організ
    0.06
     привести
    0.06
     marking
    0.06
     風
    0.06
    Є
    0.06
    .CharField
    0.06
    （
    0.06
    Act Density 0.001%

    No Known Activations