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

    Neuronpedia

    INDEX
    Explanations

    social media and continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ീസ്
    0.49
    propertyPath
    0.48
     রিজ
    0.48
    capitalize
    0.46
    feliz
    0.46
     ಔಷಧ
    0.45
     সম্মিলিত
    0.45
    បំផុត
    0.44
     ஒரே
    0.44
    ᱼ
    0.44
    POSITIVE LOGITS
    (
    0.53
    나
    0.47
    रा
    0.47
    기
    0.46
    ,
    0.44
    라
    0.44
     interviews
    0.43
    过于
    0.42
     bureaux
    0.42
    让我们
    0.42
    Act Density 0.000%

    No Known Activations