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

    Neuronpedia

    INDEX
    Explanations

    conversational prompts and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     moved
    0.36
     spatially
    0.36
     semi
    0.36
     strategically
    0.36
     structurally
    0.36
     managed
    0.35
     substrate
    0.35
     extremities
    0.35
     consistent
    0.35
     clinically
    0.35
    POSITIVE LOGITS
     какую
    0.47
     plz
    0.46
     질문
    0.45
     veuillez
    0.43
    Whats
    0.43
    caesar
    0.41
    fyp
    0.40
     какого
    0.40
    नमस्ते
    0.40
    问道
    0.39
    Act Density 0.095%

    No Known Activations