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

    Neuronpedia

    INDEX
    Explanations

    code/configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    тів
    -0.07
     koy
    -0.06
     showToast
    -0.06
     جو
    -0.06
    	em
    -0.06
     tvoř
    -0.06
     Basically
    -0.06
    �
    -0.05
    送料
    -0.05
    aleur
    -0.05
    POSITIVE LOGITS
     nội
    0.07
    -best
    0.07
    ινε
    0.06
    EMY
    0.06
     была
    0.06
     celebrate
    0.06
    ERNEL
    0.06
    .updateDynamic
    0.06
     possessed
    0.06
    051
    0.06
    Act Density 0.007%

    No Known Activations