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

    Neuronpedia

    INDEX
    Explanations

    code, academic, and technical descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Maharashtra
    0.44
     Sungai
    0.41
     Bonifacio
    0.41
     Madhya
    0.40
     Bollywood
    0.40
     Manipur
    0.39
     Mathf
    0.39
    consensus
    0.39
     Andhra
    0.39
     مشہور
    0.38
    POSITIVE LOGITS
     Assignment
    0.43
     retr
    0.43
     ORDER
    0.42
    Assignment
    0.42
    Attempt
    0.41
     아니라
    0.41
    Deadline
    0.41
     Purchase
    0.40
    Attach
    0.39
    Purchase
    0.39
    Act Density 0.000%

    No Known Activations