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

    Neuronpedia

    INDEX
    Explanations

    AI chatbot disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Drivers
    0.39
     뭐라고
    0.37
    Datei
    0.36
    र्स
    0.36
     Drugs
    0.36
     अध्या
    0.35
    Drivers
    0.35
    จํา
    0.35
    ISP
    0.34
    なんと
    0.34
    POSITIVE LOGITS
     columnist
    0.49
    Dr
    0.48
    লেখক
    0.47
     हूं
    0.46
     Dr
    0.44
    Column
    0.42
    column
    0.41
     freelance
    0.41
    <em>
    0.40
     bio
    0.40
    Act Density 0.001%

    No Known Activations