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

    Neuronpedia

    INDEX
    Explanations

    sure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ninh
    -0.07
    Benef
    -0.06
    ';";↵
    -0.06
    “As
    -0.06
    につ
    -0.06
    rupt
    -0.05
    итися
    -0.05
    (post
    -0.05
    .img
    -0.05
    .”↵
    -0.05
    POSITIVE LOGITS
     homers
    0.07
    sville
    0.07
    seg
    0.06
    .UIManager
    0.06
     parental
    0.06
    .tensor
    0.06
     yıldız
    0.06
     HR
    0.06
     академ
    0.06
     área
    0.06
    Act Density 0.000%

    No Known Activations