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

    Neuronpedia

    INDEX
    Explanations

    GSM modem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     settings
    0.51
    その
    0.51
    SETTINGS
    0.51
    エ
    0.50
     places
    0.49
     gyroscope
    0.47
     strengths
    0.47
    یا
    0.46
    Q
    0.45
    ハン
    0.45
    POSITIVE LOGITS
    க்
    0.48
     गुजराती
    0.48
    សម្រាប់
    0.47
     учетом
    0.46
    ritional
    0.46
     ignoreString
    0.46
    foration
    0.44
     స్వ
    0.44
    ពេល
    0.43
     ખો
    0.43
    Act Density 0.002%

    No Known Activations