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

    Neuronpedia

    INDEX
    Explanations

    your

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sauna
    -0.07
    еле
    -0.07
    (expression
    -0.07
    ressive
    -0.07
     groupName
    -0.06
    음을
    -0.06
    िप
    -0.06
    MODEL
    -0.06
     Arbit
    -0.06
    .floor
    -0.06
    POSITIVE LOGITS
    Listening
    0.07
     tình
    0.06
     Egg
    0.06
     Policy
    0.06
     Consultant
    0.06
     vết
    0.06
    íf
    0.06
     الاقتص
    0.06
    国際
    0.06
     matchup
    0.06
    Act Density 0.001%

    No Known Activations