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

    Neuronpedia

    INDEX
    Explanations

    chmod +x, as e

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ֽ
    0.68
    volt
    0.64
    Platz
    0.63
    float
    0.62
    bool
    0.62
     ადგილ
    0.61
    valor
    0.61
    checkmark
    0.61
    犒
    0.60
    for
    0.60
    POSITIVE LOGITS
     WebSocket
    0.52
    ラム
    0.51
     ডেভেল
    0.51
     Apache
    0.51
     Developer
    0.49
     एक्सप्रेस
    0.49
     grpc
    0.49
     api
    0.49
    ACLE
    0.48
     উত্প
    0.48
    Act Density 0.023%

    No Known Activations