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

    Neuronpedia

    INDEX
    Explanations

    graham crackers, perfect day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    androidTest
    0.40
    government
    0.39
    örü
    0.39
    hungry
    0.39
    necessary
    0.39
     सिलसिले
    0.39
    齜
    0.38
    सरकार
    0.38
     amd
    0.38
    nonatomic
    0.38
    POSITIVE LOGITS
     идеи
    0.39
     ideas
    0.38
     введен
    0.37
    CRYPT
    0.36
    -*/
    0.35
     variar
    0.35
    弹性
    0.35
     introd
    0.35
    ideas
    0.34
    變
    0.34
    Act Density 0.000%

    No Known Activations