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

    Neuronpedia

    INDEX
    Explanations

    code related to programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    online
    0.40
     pertinent
    0.39
     confident
    0.38
    ET
    0.38
    itat
    0.37
    message
    0.37
    way
    0.36
     screen
    0.36
     email
    0.36
    uds
    0.35
    POSITIVE LOGITS
     uzak
    0.46
     νη
    0.46
    澼
    0.45
     Nieder
    0.43
    菽
    0.42
    㝢
    0.42
     Durchmesser
    0.42
     দূর
    0.41
    清楚
    0.41
    یدن
    0.40
    Act Density 0.000%

    No Known Activations