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

    Neuronpedia

    INDEX
    Explanations

    chivalry Templars

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Diego
    0.58
    ings
    0.58
    adri
    0.55
    ioides
    0.55
    وني
    0.55
    తులను
    0.55
    eningen
    0.54
     martens
    0.54
    shims
    0.54
    ipennis
    0.54
    POSITIVE LOGITS
     ა
    0.59
     Стар
    0.58
    त्मक
    0.57
    рес
    0.55
    τρ
    0.55
     resor
    0.55
     Katz
    0.54
     onlyOwner
    0.54
     ২০১
    0.54
     cance
    0.53
    Act Density 0.000%

    No Known Activations