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

    Neuronpedia

    INDEX
    Explanations

    Apache license

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zoo
    0.41
     scholar
    0.40
    ʑ
    0.38
     secretário
    0.38
     scholars
    0.37
     apprentice
    0.37
    ewomen
    0.37
     discíp
    0.37
    듯
    0.37
     scheme
    0.36
    POSITIVE LOGITS
     Apache
    0.41
    永远
    0.39
     apropri
    0.38
     така
    0.38
    Hector
    0.38
     відповід
    0.37
     такими
    0.37
    构成
    0.37
    amazing
    0.36
     Dread
    0.36
    Act Density 0.000%

    No Known Activations