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

    Neuronpedia

    INDEX
    Explanations

    explanation of concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lic
    0.42
     pán
    0.42
     license
    0.41
     parameter
    0.39
     מג
    0.38
     organic
    0.38
    สถานที่
    0.38
     voie
    0.38
     din
    0.37
     line
    0.37
    POSITIVE LOGITS
    CameraOpened
    0.45
     इंपॉर्ट
    0.43
    importanza
    0.40
    datetime
    0.38
    InitFlag
    0.37
     Яро
    0.37
     ita
    0.36
    AINLESS
    0.36
    stra
    0.36
    odec
    0.36
    Act Density 0.000%

    No Known Activations