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

    Neuronpedia

    INDEX
    Explanations

    right to privacy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diritti
    0.44
     direitos
    0.43
    ಳ್ಳಿ
    0.40
    ctuaries
    0.40
    žila
    0.40
    ारखंड
    0.39
    权利
    0.39
     autonomously
    0.39
    Ơ
    0.39
    autoarima
    0.38
    POSITIVE LOGITS
     পর্যাপ্ত
    0.42
    pad
    0.41
     adequate
    0.41
     karn
    0.40
     Adequate
    0.40
    pell
    0.39
     fair
    0.39
    rus
    0.37
     भूख
    0.37
    急性
    0.37
    Act Density 0.007%

    No Known Activations