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

    Neuronpedia

    INDEX
    Explanations

    Salesforce CRM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    that
    0.56
    at
    0.51
    、
    0.50
     that
    0.48
    って
    0.48
    觓
    0.46
     অস
    0.45
     یا
    0.44
     Lectures
    0.43
    遍历
    0.43
    POSITIVE LOGITS
    UTER
    0.61
    ści
    0.57
     deced
    0.50
    ET
    0.49
     ROUILLER
    0.48
     osobe
    0.47
     rusa
    0.47
     saúde
    0.47
    OTH
    0.47
     reluct
    0.47
    Act Density 0.001%

    No Known Activations