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

    Neuronpedia

    INDEX
    Explanations

    banking debt commitment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.58
    da
    0.56
    v
    0.55
    ists
    0.54
    us
    0.53
    nt
    0.53
    AM
    0.53
    IM
    0.52
    ons
    0.52
    ats
    0.52
    POSITIVE LOGITS
    PAssignment
    0.51
     الطلبه
    0.49
     европей
    0.49
     خمسه
    0.48
     baseApiPath
    0.48
     neoplastic
    0.48
    ləş
    0.48
     multiuser
    0.47
     keyValue
    0.47
     euclidean
    0.46
    Act Density 0.001%

    No Known Activations