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

    Neuronpedia

    INDEX
    Explanations

    women wear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     గుర్
    0.41
     UCLA
    0.38
    别
    0.38
     condo
    0.37
     Property
    0.37
    Cone
    0.36
     Equality
    0.36
     YMCA
    0.35
    ሚ
    0.35
     Cone
    0.35
    POSITIVE LOGITS
    randint
    0.42
    actin
    0.40
    effici
    0.40
    reviewed
    0.39
    證據
    0.38
    єн
    0.38
    ̣t
    0.37
    scientist
    0.37
    ۇل
    0.37
    amples
    0.36
    Act Density 0.000%

    No Known Activations