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

    Neuronpedia

    INDEX
    Explanations

    titles and names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Thema
    0.49
    ภัย
    0.48
     audiencia
    0.47
    朝
    0.47
     भोज
    0.47
     Phát
    0.47
    రుపు
    0.46
    Roxy
    0.46
     Concurrent
    0.46
     Rocca
    0.46
    POSITIVE LOGITS
     Mr
    1.02
    Mr
    0.94
     mr
    0.78
     Jimmy
    0.75
    Jimmy
    0.75
     Molly
    0.74
     Messrs
    0.72
     Mister
    0.69
     Miss
    0.65
     before
    0.63
    Act Density 0.000%

    No Known Activations