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

    Neuronpedia

    INDEX
    Explanations

    formal/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     touristes
    -0.50
     parede
    -0.50
     forcément
    -0.49
    liğini
    -0.48
    omores
    -0.48
     tarko
    -0.47
     réfugiés
    -0.47
     pewno
    -0.46
     alliés
    -0.46
    حات
    -0.46
    POSITIVE LOGITS
     Wicidata
    0.68
    WHEREAS
    0.64
     epo
    0.63
     متعلقه
    0.61
     препратки
    0.60
    /******/
    0.59
    EndContext
    0.59
     splen
    0.57
     indistingu
    0.57
     ablation
    0.57
    Act Density 0.355%

    No Known Activations