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

    Neuronpedia

    INDEX
    Explanations

    names, particularly associated with locations and individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Protobuf
    -0.53
    RefNanny
    -0.50
     Biôgrafia
    -0.48
     Gaud
    -0.47
    Funky
    -0.46
    Jereo
    -0.45
     fum
    -0.45
     Molo
    -0.45
     Funky
    -0.42
    hithe
    -0.42
    POSITIVE LOGITS
     Carlisle
    2.73
    lisle
    2.20
     Carlyle
    0.89
     Cumbria
    0.88
     Carleton
    0.68
    Carly
    0.54
     Carly
    0.52
     Carson
    0.52
     McLean
    0.51
     Carla
    0.50
    Act Density 0.001%

    No Known Activations