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

    Neuronpedia

    INDEX
    Explanations

    clears, boundaries, worry, below

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nate
    0.49
     Pusat
    0.47
     relacionamento
    0.47
     Proyecto
    0.46
     partenariat
    0.46
     pairing
    0.46
     negociación
    0.45
     Liaison
    0.44
     Jej
    0.44
     Saison
    0.44
    POSITIVE LOGITS
    石
    0.46
     камен
    0.46
    หล
    0.45
     upang
    0.44
     могат
    0.42
     труб
    0.42
     금
    0.41
    ทำ
    0.41
    丷
    0.40
    ਘ
    0.40
    Act Density 0.016%

    No Known Activations