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

    Neuronpedia

    INDEX
    Explanations

    be part

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     legislative
    0.61
     legislator
    0.56
     filmmaking
    0.54
     corruption
    0.53
     phishing
    0.53
     benzyl
    0.52
     bribery
    0.52
     espionage
    0.52
     spyware
    0.51
     tragedy
    0.50
    POSITIVE LOGITS
    ㅅ
    0.49
    aliśmy
    0.48
    อน
    0.47
     ahí
    0.47
    addNew
    0.47
    ahkan
    0.47
     pertama
    0.45
    腳
    0.45
     addNew
    0.45
    elif
    0.45
    Act Density 0.000%

    No Known Activations