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

    Neuronpedia

    INDEX
    Explanations

    Calendar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     어�
    -0.07
    ít
    -0.06
    ria
    -0.06
    rypt
    -0.06
     깨
    -0.06
    Salt
    -0.06
     BLUE
    -0.06
     Exist
    -0.06
     alt
    -0.06
    issa
    -0.06
    POSITIVE LOGITS
    ότητας
    0.06
    bservice
    0.06
    ],↵↵
    0.06
     enquiries
    0.06
     canadian
    0.06
    IOD
    0.06
    Calculator
    0.06
    işim
    0.06
     COMMENTS
    0.06
     incel
    0.06
    Act Density 0.001%

    No Known Activations