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

    Neuronpedia

    INDEX
    Explanations

    father figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SC
    0.89
     LRC
    0.89
    SC
    0.83
     IAS
    0.79
     Simons
    0.79
    camp
    0.78
     Campbell
    0.75
    alls
    0.75
     Swain
    0.74
     Clem
    0.74
    POSITIVE LOGITS
     Father
    1.06
     father
    1.04
    Father
    1.01
     DHT
    0.99
     TET
    0.95
     fathers
    0.90
     padre
    0.90
     père
    0.88
    DHT
    0.88
     Vater
    0.88
    Act Density 2.617%

    No Known Activations