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

    Neuronpedia

    INDEX
    Explanations

    stage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    浥
    -0.06
     Aviation
    -0.06
     Applicant
    -0.06
     scaled
    -0.06
    سوق
    -0.06
    货运
    -0.06
     kilomet
    -0.06
    优质的
    -0.06
      
↵
↵
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    important
    0.07
    //'
    0.07
     Chall
    0.07
     playoffs
    0.07
     maken
    0.07
    Neill
    0.07
    פלא
    0.07
     Alto
    0.07
    נחש
    0.07
    澶
    0.07
    Act Density 0.002%

    No Known Activations