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

    Neuronpedia

    INDEX
    Explanations

    advice encouragement thinking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     đóng
    -0.08
     სადაც
    -0.08
     որտեղ
    -0.08
     destroying
    -0.08
     aquela
    -0.08
     interp
    -0.08
     самолет
    -0.08
     дзе
    -0.07
    .destroy
    -0.07
     Shrine
    -0.07
    POSITIVE LOGITS
     derfor
    0.08
    798
    0.08
     instinct
    0.08
     bunu
    0.08
     därför
    0.08
    Lu
    0.08
    Wenn
    0.08
    これは
    0.07
    748
    0.07
     homem
    0.07
    Act Density 0.636%

    No Known Activations