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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Joshua
    0.88
    Joshua
    0.81
     Isabella
    0.76
     Ava
    0.72
     Benjamin
    0.71
    Ethan
    0.68
     Abigail
    0.68
     Ethan
    0.67
     Bella
    0.65
     Mia
    0.64
    POSITIVE LOGITS
    Mike
    0.62
     Mike
    0.57
     tri
    0.57
    Dan
    0.54
     Dan
    0.53
     ඕ
    0.52
     DAN
    0.51
    Phil
    0.51
    Steve
    0.51
    hjust
    0.50
    Act Density 0.016%

    No Known Activations