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

    Neuronpedia

    INDEX
    Explanations

    cat and category

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SOB
    0.49
     Tekh
    0.45
    URUK
    0.44
     Eğ
    0.42
     Pek
    0.41
     Sozial
    0.40
     Giuliani
    0.40
     Tend
    0.40
     Aktivitäten
    0.40
    മുഖ
    0.40
    POSITIVE LOGITS
    cat
    0.97
    Cat
    0.93
     Cat
    0.92
     cat
    0.85
     CAT
    0.81
    agory
    0.79
     catast
    0.75
    猫
    0.72
     cathe
    0.71
    aclysm
    0.71
    Act Density 0.022%

    No Known Activations