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

    Neuronpedia

    INDEX
    Explanations

    P+ word beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     उत्सर्जन
    0.35
     అంశ
    0.35
    itettura
    0.35
    वास्तव
    0.33
     काउंसलिंग
    0.33
    薁
    0.32
    CategoryImage
    0.31
    ༻
    0.31
    \}}
    0.30
    clarinet
    0.30
    POSITIVE LOGITS
    P
    0.60
     P
    0.57
     p
    0.55
    incipal
    0.55
    p
    0.55
    urpose
    0.49
    <0x89>
    0.47
     п
    0.46
     پ
    0.46
     พ
    0.46
    Act Density 0.102%

    No Known Activations